© 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. 38090
    Prev
    Next
    INDEX
    Explanations

    Shujin, Sujihiki, Santoku, Suja, Shuji, Sujeong-gu

    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
    ar
    0.94
    t
    0.94
    ig
    0.93
    in
    0.91
    "
    0.87
    ต
    0.82
    al
    0.80
    as
    0.73
    an
    0.71
    im
    0.70
    POSITIVE LOGITS
    ции
    0.72
    м
    0.71
    ы
    0.70
     (
    0.70
    دي
    0.68
     aument
    0.67
    ва
    0.66
     crece
    0.66
    ک
    0.66
    защи
    0.65
    Activations Density 0.000%

    No Known Activations