© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209502
    Prev
    Next
    INDEX
    Explanations

    tic-tac-toe

    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_25_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
     Temporary
    0.38
    Temporary
    0.38
     đế
    0.37
    WEEK
    0.37
    ']);
    0.36
     de
    0.35
    SUP
    0.35
    ларды
    0.35
    Ngày
    0.35
     lỗi
    0.34
    POSITIVE LOGITS
     Fase
    0.51
     Hausdorff
    0.47
    荅
    0.44
    testimonials
    0.43
     गणित
    0.42
     кожен
    0.41
    ジュエリー
    0.40
     fase
    0.40
     junit
    0.40
     chess
    0.39
    Activations Density 0.004%

    No Known Activations