© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121376
    Prev
    Next
    INDEX
    Explanations

    fish and related concepts

    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_37_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
     pescado
    0.57
    鱼
    0.55
     fish
    0.52
    Fish
    0.49
     Fish
    0.48
     মাছ
    0.48
    🐟
    0.48
    魚
    0.47
     मछली
    0.44
     pesce
    0.44
    POSITIVE LOGITS
     censorship
    0.43
     curses
    0.41
    カイブ
    0.41
    curses
    0.40
    이트
    0.39
     النظر
    0.39
     censored
    0.39
     Celtic
    0.38
     sân
    0.38
     Canaan
    0.38
    Activations Density 0.003%

    No Known Activations