© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211791
    Prev
    Next
    INDEX
    Explanations

    section separators and titles

    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_20_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
    铬
    0.50
     rampant
    0.44
     seyd
    0.44
     comand
    0.43
    <%
    0.43
    閎
    0.42
    鉻
    0.42
    🎓
    0.42
     bandas
    0.42
    ದಾರ
    0.41
    POSITIVE LOGITS
    冷蔵
    0.46
     PayPay
    0.44
    зи
    0.42
    subseteq
    0.41
     والله
    0.41
     UIScrollView
    0.41
    ,_-
    0.41
    Delta
    0.40
     CtApp
    0.40
     നിര്‍
    0.40
    Activations Density 0.000%

    No Known Activations