© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129555
    Prev
    Next
    INDEX
    Explanations

    jump

    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_50_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
    咙
    0.43
    खंड
    0.39
     hä
    0.38
    鏑
    0.38
    гно
    0.38
     বান
    0.38
    鴟
    0.37
    الي
    0.37
    лів
    0.37
     ts
    0.37
    POSITIVE LOGITS
    umping
    0.47
    ợ
    0.45
    UMPS
    0.43
    UMP
    0.40
     Horne
    0.39
    Path
    0.39
    مہ
    0.38
    Rush
    0.38
    cra
    0.38
    mata
    0.38
    Activations Density 0.020%

    No Known Activations