© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27664
    Prev
    Next
    INDEX
    Explanations

    Chinatown restaurants

    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_10_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
    ي
    0.77
    ;
    0.67
    Дру
    0.63
    i
    0.62
     [];
    0.62
    iTunes
    0.59
    Я
    0.59
    П
    0.58
    이랑
    0.57
    ر
    0.57
    POSITIVE LOGITS
    omicide
    0.66
     Chavez
    0.61
    arem
    0.60
    uksi
    0.59
    ActionResult
    0.57
    achi
    0.55
    ativos
    0.55
     Thai
    0.52
     Chinatown
    0.52
     Māori
    0.52
    Activations Density 0.020%

    No Known Activations