© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62488
    Prev
    Next
    INDEX
    Explanations

    single unit

    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
    ку
    0.66
    𝚋
    0.66
    ):["
    0.65
     цветов
    0.61
    کرو
    0.61
    poetrylovers
    0.58
    setosa
    0.57
    owymi
    0.57
    맏
    0.57
     красо
    0.56
    POSITIVE LOGITS
     Prayer
    0.58
     are
    0.57
     School
    0.57
     is
    0.56
     lake
    0.55
    ne
    0.55
    ija
    0.55
     Centre
    0.54
    เหลือ
    0.54
    to
    0.54
    Activations Density 0.016%

    No Known Activations