© 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. 49913
    Prev
    Next
    INDEX
    Explanations

    apple. doctor. cliff. goat. horse. Lottery

    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
    盟
    0.34
    affle
    0.33
    Aff
    0.31
    棱
    0.30
    Recent
    0.29
     contextual
    0.29
    zer
    0.28
     Tir
    0.28
     Recent
    0.28
    LISTEN
    0.28
    POSITIVE LOGITS
     takich
    0.34
    𒉆
    0.33
    drinking
    0.32
     Muñoz
    0.31
    喍
    0.31
     liền
    0.31
    زمانہ
    0.31
    畢
    0.31
     vídeo
    0.31
     免
    0.30
    Activations Density 0.007%

    No Known Activations