© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193224
    Prev
    Next
    INDEX
    Explanations

    viscera, eviscerated, viscosities

    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_4_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
    し
    1.30
    ین
    1.11
    ines
    1.06
    in
    1.02
    ग
    1.00
    bies
    0.99
    न
    0.98
    st
    0.98
    ies
    0.93
    ER
    0.93
    POSITIVE LOGITS
    ى
    1.47
    ur
    1.22
    ри
    1.22
    ור
    1.16
    то
    1.04
    দের
    0.99
    ري
    0.97
    يد
    0.96
    يز
    0.93
    רט
    0.92
    Activations Density 0.002%

    No Known Activations