© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195218
    Prev
    Next
    INDEX
    Explanations

    what goes

    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_9_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
    0.33
    a
    0.33
    い
    0.29
    et
    0.28
    ,
    0.28
    家
    0.27
    v
    0.27
    אר
    0.27
    il
    0.26
    व
    0.26
    POSITIVE LOGITS
     Комп
    0.29
     فيلم
    0.29
     have
    0.29
     Ми
    0.28
     ي
    0.28
     hinzuge
    0.28
     ಈಗಾಗಲೇ
    0.28
     студент
    0.27
     Мо
    0.27
    mation
    0.27
    Activations Density 0.018%

    No Known Activations