© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 203329
    Prev
    Next
    INDEX
    Explanations

    slash command builder

    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_6_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
    ,
    0.82
    ва
    0.77
    มัน
    0.71
    ט
    0.70
    rzeć
    0.69
    ל
    0.69
    -
    0.69
     surmounted
    0.68
     materialized
    0.68
    ก
    0.68
    POSITIVE LOGITS
    as
    0.91
    ot
    0.87
    و
    0.86
     as
    0.82
    Е
    0.82
    AR
    0.78
     Ducati
    0.75
    I
    0.73
     Tattha
    0.73
     மிகவும்
    0.72
    Activations Density 0.000%

    No Known Activations