© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36217
    Prev
    Next
    INDEX
    Explanations

    process called

    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_11_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
    as
    0.55
    i
    0.55
    coords
    0.55
    駒
    0.51
    thinkable
    0.51
    teis
    0.49
     preocupación
    0.49
     artículos
    0.48
     dólares
    0.48
     crónica
    0.48
    POSITIVE LOGITS
    t
    0.68
    yorum
    0.59
    ү
    0.57
    у
    0.57
    ್‌
    0.56
     Roasted
    0.56
    ופ
    0.56
    ு
    0.55
    ation
    0.55
     Monuments
    0.54
    Activations Density 0.003%

    No Known Activations