© 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. 34162
    Prev
    Next
    INDEX
    Explanations

    Debussy or DBSCAN

    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
    in
    0.73
    يل
    0.71
     Públic
    0.70
    up
    0.66
    la
    0.66
    va
    0.65
    娌
    0.64
    ックス
    0.63
    в
    0.63
    app
    0.62
    POSITIVE LOGITS
    ی
    1.00
    }
    0.75
    :}
    0.68
    (-
    0.67
    ס
    0.67
    ्स
    0.66
    ?";
    0.65
    *;
    0.64
    :“
    0.64
     یکی
    0.63
    Activations Density 0.001%

    No Known Activations