© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27806
    Prev
    Next
    INDEX
    Explanations

    verceljs.com

    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
     beach
    0.48
     दक्षिणी
    0.39
     MainPage
    0.38
     computable
    0.37
    ʟ
    0.37
     computational
    0.36
     codebase
    0.36
     landowners
    0.35
    地形
    0.35
     multiplets
    0.35
    POSITIVE LOGITS
    嵇
    0.38
    BOARD
    0.37
    Hear
    0.37
    гъл
    0.37
    eluarkan
    0.37
    Elliott
    0.36
    Helen
    0.36
    amment
    0.36
    有料
    0.36
     juan
    0.35
    Activations Density 0.011%

    No Known Activations