© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126575
    Prev
    Next
    INDEX
    Explanations

    subtraction

    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_37_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
     दर्शन
    0.38
    爫
    0.38
     আব
    0.38
     hast
    0.38
    搐
    0.38
     পড়
    0.36
     Aiden
    0.36
    func
    0.35
    hts
    0.35
    เคล
    0.34
    POSITIVE LOGITS
     minus
    1.56
    minus
    1.41
     Minus
    1.41
    Minus
    1.34
     минус
    1.30
     माइनस
    0.98
     subtract
    0.92
    减
    0.91
     subtracting
    0.90
     Subtract
    0.86
    Activations Density 0.003%

    No Known Activations