© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38695
    Prev
    Next
    INDEX
    Explanations

    Formula 1, motorsport, sports championships

    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_11_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
     adore
    0.52
    ğunu
    0.52
    andaag
    0.52
     disprove
    0.52
     straighten
    0.52
     jornalista
    0.52
    🌇
    0.52
     जाएगा
    0.51
     jLabel
    0.50
    enje
    0.50
    POSITIVE LOGITS
     시작
    0.70
    剣
    0.60
    BEGIN
    0.57
    äst
    0.56
    :$
    0.55
    enziali
    0.54
    is
    0.54
    first
    0.53
    start
    0.53
    ತ್ರ
    0.53
    Activations Density 0.007%

    No Known Activations