© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108406
    Prev
    Next
    INDEX
    Explanations

    .js or .mjs files

    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_2_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
    ור
    1.55
     are
    1.48
     it
    1.46
     can
    1.43
    т
    1.35
     you
    1.32
     be
    1.31
    ра
    1.23
     for
    1.22
    ع
    1.20
    POSITIVE LOGITS
    G
    1.04
    ного
    1.02
    kových
    0.97
    Z
    0.95
    žení
    0.94
    ávan
    0.92
    oucí
    0.89
    Кра
    0.89
    ával
    0.89
    áin
    0.88
    Activations Density 0.000%

    No Known Activations