© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30482
    Prev
    Next
    INDEX
    Explanations

    dime

    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
    Negative Logits
    wj
    0.49
    纭
    0.48
    きましょう
    0.48
    谴
    0.46
    ेंगी
    0.46
     оши
    0.45
    хів
    0.45
    wb
    0.44
    箕
    0.44
    朐
    0.44
    POSITIVE LOGITS
     successively
    0.43
     এতটা
    0.41
    ্বার
    0.40
    {"
    0.40
    datos
    0.40
     חש
    0.40
    diethyl
    0.39
     POLL
    0.39
     Answer
    0.39
    ">−</
    0.39
    Activations Density 0.000%

    No Known Activations