© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196198
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     V
    0.45
     Venus
    0.44
    $~
    0.42
     skyscrapers
    0.38
    '।
    0.38
    Venus
    0.38
    Ｖ
    0.38
     Numerical
    0.38
     suficientes
    0.37
    ﾇ
    0.36
    POSITIVE LOGITS
    fo
    0.61
     Fou
    0.58
    FO
    0.54
     fou
    0.47
    fou
    0.47
     Fo
    0.46
    Fo
    0.45
     fo
    0.45
    褔
    0.44
    FG
    0.44
    Activations Density 0.003%

    No Known Activations