© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226302
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or other numbers

    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_10_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
    p
    0.60
    M
    0.56
    G
    0.56
    с
    0.55
    .
    0.54
    س
    0.54
    N
    0.53
    名
    0.51
    D
    0.51
    িন
    0.49
    POSITIVE LOGITS
     essais
    0.57
     істо
    0.53
     embank
    0.52
     interdiscipl
    0.49
     лабора
    0.49
     Ι
    0.48
     université
    0.48
     anticon
    0.47
     procedure
    0.46
     здра
    0.46
    Activations Density 0.006%

    No Known Activations