© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5381
    Prev
    Next
    INDEX
    Explanations

    power supply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    txtbtn
    0.39
    vap
    0.38
    OnFile
    0.37
     पिंडदान
    0.37
     گیر
    0.37
    био
    0.37
    িয়া
    0.36
     期
    0.36
    сын
    0.35
    東海
    0.35
    POSITIVE LOGITS
     PSU
    1.05
     power
    1.04
    电源
    0.94
    電源
    0.89
     Power
    0.87
    Power
    0.86
     supply
    0.84
    power
    0.83
     पावर
    0.75
    PS
    0.72
    Activations Density 0.038%

    No Known Activations