© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194186
    Prev
    Next
    INDEX
    Explanations

    Catalina Sky Survey

    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_15_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
     stato
    0.53
     фар
    0.50
     rappresent
    0.49
    💧
    0.48
     continuare
    0.48
     гимна
    0.48
    摄像
    0.48
    Arti
    0.47
    〉
    0.47
     giocatori
    0.46
    POSITIVE LOGITS
    mar
    0.49
     возможно
    0.49
    >[
    0.48
    aha
    0.47
    หา
    0.47
    なに
    0.47
     способность
    0.46
    ar
    0.45
    arik
    0.45
     ممکن
    0.45
    Activations Density 0.000%

    No Known Activations