Higher-radix floating-point representations have the potential for higher performance, lower energy footprint, and reduced gate count in embedded systems when compared to traditional binary floating-point numbers. Thus, they might also appear in transmission of sensor data values. However, these number formats introduce redundancies, which can be exploited for steganographic message transfer. We present a covert channel that exploits this redundancy and can trade steganographic bandwidth against introduced error and thus detectability. In the basic variant, the covert channel is fully reversible, i.e., not detectable from the data. Experiments with an implementation illustrate that detectability via compressibility metric, Shannon entropy and bi-grams is possible depending on how aggressive bandwidth is pushed.