© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137620
    Prev
    Next
    INDEX
    Explanations

    John Wick or Keanu Reeves movies

    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_12_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
    言葉
    0.54
     mów
    0.50
     আহ্ব
    0.48
     ಮಾತ್ರ
    0.48
    ↵↵↵↵↵↵↵
    0.47
     weave
    0.47
    ਫ਼
    0.47
    itance
    0.47
     mówi
    0.46
     wasting
    0.46
    POSITIVE LOGITS
     مشر
    0.58
    ก
    0.57
    G
    0.56
     fler
    0.54
    я
    0.53
    تون
    0.51
    <0xE9>
    0.51
    ни
    0.50
     ก
    0.50
    тель
    0.50
    Activations Density 0.000%

    No Known Activations