© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221447
    Prev
    Next
    INDEX
    Explanations

    bonus features, levels, characters, enemies

    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_10_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
     I
    0.34
    #
    0.34
    "
    0.34
     Shelter
    0.33
    ées
    0.31
    El
    0.31
    و
    0.31
     Closer
    0.31
    Un
    0.30
    lo
    0.30
    POSITIVE LOGITS
    лна
    0.38
    和服务
    0.33
    ﺖ
    0.32
    циона
    0.31
    лни
    0.31
    នៃ
    0.31
    帝国
    0.31
     spä
    0.31
    μένη
    0.30
    ದಲ್ಲಿ
    0.30
    Activations Density 0.023%

    No Known Activations