© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122248
    Prev
    Next
    INDEX
    Explanations

    up or down conversion

    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_3_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
    つける
    0.70
     tích
    0.69
     chale
    0.69
     fortes
    0.68
     contenders
    0.67
     rumen
    0.66
    -
    0.66
     znajdu
    0.66
     yon
    0.66
     quatro
    0.65
    POSITIVE LOGITS
    os
    0.85
    endsWith
    0.75
    un
    0.73
    ات
    0.73
    on
    0.73
    down
    0.72
    as
    0.71
    з
    0.71
    aub
    0.70
    in
    0.64
    Activations Density 0.001%

    No Known Activations