© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68624
    Prev
    Next
    INDEX
    Explanations

    code imports

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    from
    0.35
    <0xC2>
    0.34
     capabilities
    0.34
    Context
    0.33
    ان
    0.33
     Mitchell
    0.32
    Id
    0.32
    capabilities
    0.32
    here
    0.32
    constants
    0.32
    POSITIVE LOGITS
     farmac
    0.39
     quảng
    0.37
    🇻
    0.37
     применять
    0.37
     Surname
    0.37
     fasi
    0.37
     savait
    0.36
    닼
    0.36
     savun
    0.35
    ഠ
    0.35
    Activations Density 0.001%

    No Known Activations