© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15655
    Prev
    Next
    INDEX
    Explanations

    alcohol and food consumption

    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_40_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
     Grid
    0.39
     Authentic
    0.38
    ♖
    0.37
     GRID
    0.36
     Fant
    0.36
     grid
    0.35
     Physics
    0.35
    赜
    0.35
     Jok
    0.35
     fác
    0.34
    POSITIVE LOGITS
     wine
    1.49
    Wine
    1.41
     Wine
    1.40
    wine
    1.29
    ワイン
    1.24
     wijn
    1.19
     wines
    1.12
     вино
    1.11
     vino
    1.09
     vinho
    1.06
    Activations Density 0.055%

    No Known Activations