© 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. 154308
    Prev
    Next
    INDEX
    Explanations

    semantics

    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
     bathing
    0.40
     crust
    0.40
    ટ્સ
    0.39
     CIE
    0.39
    岳
    0.39
     রাজেশ
    0.38
    ゾ
    0.38
    ウォ
    0.38
    jons
    0.38
     Wals
    0.37
    POSITIVE LOGITS
    Sem
    1.97
     semantic
    1.95
    Semantic
    1.95
     Sem
    1.92
     Semantic
    1.90
    semantic
    1.88
     semantics
    1.83
    Seminar
    1.71
     Semin
    1.70
     semin
    1.66
    Activations Density 0.001%

    No Known Activations