© 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. 166537
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     කොට
    0.39
    羰
    0.38
     Fmat
    0.37
     FMT
    0.37
     TAU
    0.36
     gustaría
    0.36
     kuhusu
    0.36
    삿
    0.36
     DBT
    0.35
    מות
    0.35
    POSITIVE LOGITS
    revenue
    0.37
     डेड
    0.36
     volo
    0.35
    舧
    0.35
     camadas
    0.34
     commanding
    0.34
     ஏனெ
    0.34
     prov
    0.33
    ason
    0.33
    stock
    0.33
    Activations Density 0.000%

    No Known Activations