© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48822
    Prev
    Next
    INDEX
    Explanations

    frequency of maintenance or changes

    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
    Ⅴ
    0.36
     Boats
    0.35
     Nodes
    0.35
     Buffered
    0.33
     Bracket
    0.33
     brackets
    0.32
     Scene
    0.32
     Nights
    0.32
    ндан
    0.32
    ᒡ
    0.31
    POSITIVE LOGITS
     scheduled
    0.39
     الملف
    0.37
     車
    0.35
    次回
    0.34
    ECO
    0.33
     aler
    0.33
    定期
    0.33
     petty
    0.32
     ECO
    0.32
    scheduled
    0.32
    Activations Density 0.002%

    No Known Activations