© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220119
    Prev
    Next
    INDEX
    Explanations

    most frequent value

    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_31_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
     причин
    0.37
    ᅣ
    0.37
    绝
    0.33
     Between
    0.32
    টর
    0.32
    Paged
    0.32
    horizontal
    0.31
    ｮ
    0.31
    лама
    0.30
    Between
    0.30
    POSITIVE LOGITS
    頻
    0.36
     freq
    0.36
     frequency
    0.35
     borrows
    0.35
     matemat
    0.34
    Frequency
    0.34
     성공
    0.33
     borrow
    0.33
     Frequency
    0.33
     статисти
    0.33
    Activations Density 0.003%

    No Known Activations