© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108275
    Prev
    Next
    INDEX
    Explanations

    inevitability, Nifty, banquet

    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_1_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
    tet
    1.09
    tion
    1.02
    ان
    1.01
    ni
    1.01
    tu
    0.99
    t
    0.98
    table
    0.95
    namen
    0.95
    toa
    0.93
    大
    0.93
    POSITIVE LOGITS
    ר
    1.70
    р
    1.27
     comprends
    1.08
     キッチン
    1.05
    '">
    1.05
     ສ
    1.02
    ิ
    1.01
    ر
    1.00
     carelessly
    0.93
    ্কে
    0.91
    Activations Density 0.000%

    No Known Activations