© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121606
    Prev
    Next
    INDEX
    Explanations

    Russian and other Slavic languages

    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
    Negative Logits
    ς
    0.92
    t
    0.79
    ني
    0.73
    м
    0.73
    ли
    0.71
    к
    0.71
    х
    0.71
     যশোরের
    0.68
    т
    0.68
    scrollHeight
    0.66
    POSITIVE LOGITS
    _
    1.21
    ol
    0.95
    ä
    0.91
    ast
    0.87
    på
    0.81
    надцать
    0.81
    olot
    0.80
    owymi
    0.78
    ab
    0.77
    า
    0.77
    Activations Density 0.001%

    No Known Activations