© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59107
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    इंडीज
    0.45
    lamualaikum
    0.45
     Crystallogr
    0.45
    嘜
    0.43
    畋
    0.41
     portland
    0.41
    cherichia
    0.40
    རྒྱ
    0.40
    篒
    0.40
     परिवहन
    0.39
    POSITIVE LOGITS
    &
    0.58
    /
    0.57
    É
    0.55
    [
    0.53
    ă
    0.50
    ,[
    0.49
    T
    0.49
    ü
    0.47
    Á
    0.47
    V
    0.46
    Activations Density 0.002%

    No Known Activations