© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201011
    Prev
    Next
    INDEX
    Explanations

    provinces

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ске
    0.39
    ::$
    0.37
     ਡ
    0.37
     शर्म
    0.37
     affect
    0.37
     strengthen
    0.36
    orean
    0.36
    üst
    0.35
    羁
    0.35
    scr
    0.35
    POSITIVE LOGITS
     thre
    0.49
     Provinc
    0.45
     Provincial
    0.45
     Province
    0.45
     Provence
    0.45
     provinsi
    0.45
     provinc
    0.44
    province
    0.44
     provincial
    0.43
     Oud
    0.43
    Activations Density 0.002%

    No Known Activations