© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127017
    Prev
    Next
    INDEX
    Explanations

    file metadata identifiers

    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_3_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
    ।
    0.91
    ای
    0.77
    кі
    0.71
    ations
    0.71
    دی
    0.70
    toxicity
    0.70
    credit
    0.70
     histological
    0.67
     typesetting
    0.66
    لی
    0.66
    POSITIVE LOGITS
    ي
    0.95
    י
    0.83
    هلاك
    0.67
     زاويه
    0.67
     praktisch
    0.66
     bauen
    0.64
     strane
    0.63
     součas
    0.63
    مكن
    0.63
     ليس
    0.63
    Activations Density 0.001%

    No Known Activations