© 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. 84614
    Prev
    Next
    INDEX
    Explanations

    converted to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ו
    1.68
    ро
    1.63
    ів
    1.61
    가
    1.46
    ри
    1.39
    д
    1.36
    larda
    1.34
    ள்
    1.34
    ம்
    1.32
    다
    1.31
    POSITIVE LOGITS
     (
    1.57
    h
    1.54
     in
    1.49
    type
    1.48
     =
    1.44
     +
    1.42
    j
    1.42
     an
    1.40
    t
    1.38
    -
    1.38
    Activations Density 0.002%

    No Known Activations