© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1774
    Prev
    Next
    INDEX
    Explanations

    drawing functions

    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_40_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
     Vimeo
    0.39
    生理
    0.37
    持ち
    0.37
     Exptl
    0.37
     HMS
    0.36
     plu
    0.36
     livid
    0.36
    🦵
    0.36
     Dunbar
    0.35
     Posters
    0.35
    POSITIVE LOGITS
     draw
    0.98
    draw
    0.96
    Draw
    0.95
     drawing
    0.93
     draws
    0.92
     Draw
    0.90
    Drawing
    0.88
     graphics
    0.87
     Drawing
    0.86
     Draws
    0.86
    Activations Density 0.190%

    No Known Activations