© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155777
    Prev
    Next
    INDEX
    Explanations

    website, documentation

    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_60_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
    (
    0.75
     (
    0.62
    <0x0D>
    0.40
    Trung
    0.38
    （
    0.38
    刓
    0.38
    鈁
    0.37
    stice
    0.36
     cua
    0.36
    biti
    0.36
    POSITIVE LOGITS
    '
    1.03
     itself
    1.01
    本身
    0.76
    ’
    0.61
    '[
    0.57
     자체
    0.54
     look
    0.54
     Tied
    0.53
     자체가
    0.51
    ׳
    0.50
    Activations Density 0.003%

    No Known Activations