© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36358
    Prev
    Next
    INDEX
    Explanations

    charcoal, burning, flames, smoke

    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_31_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
     shap
    0.42
     hauled
    0.39
     tid
    0.39
     transported
    0.37
     tract
    0.36
    藓
    0.36
     tossed
    0.36
     jost
    0.33
    ഠ
    0.33
     ejected
    0.33
    POSITIVE LOGITS
     burning
    0.86
    Burning
    0.81
     Burning
    0.79
    burning
    0.77
    燒
    0.77
    火焰
    0.75
     flames
    0.74
     burned
    0.73
     burnt
    0.71
     burners
    0.70
    Activations Density 0.044%

    No Known Activations