© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78295
    Prev
    Next
    INDEX
    Explanations

    Foundations

    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_0_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
     (
    1.89
    ه
    1.66
    in
    1.63
    ال
    1.56
    د
    1.48
    inį
    1.41
    ان
    1.40
    i
    1.37
    src
    1.34
    ה
    1.34
    POSITIVE LOGITS
    ↵
    2.09
    '
    1.73
    "
    1.66
    <0x0D>
    1.54
    ó
    1.52
    -
    1.48
    ,
    1.47
    é
    1.45
    </h3>
    1.38
    :
    1.32
    Activations Density 0.001%

    No Known Activations