© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164344
    Prev
    Next
    INDEX
    Explanations

    scenarioDavid wantscolleague isSomeone constantlyIf a doctor tells you

    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_31_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
    氐
    0.34
     মাঝ
    0.28
     Stephenson
    0.28
    刷新
    0.28
     officinalis
    0.28
     revital
    0.28
     resale
    0.28
     resonates
    0.28
    的作品
    0.27
    凧
    0.27
    POSITIVE LOGITS
    धील
    0.31
    Hist
    0.30
     alte
    0.30
    HIST
    0.30
     kandid
    0.30
    OCK
    0.29
     histone
    0.29
     berlin
    0.29
     लसी
    0.28
    hist
    0.28
    Activations Density 0.000%

    No Known Activations