© 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. 93090
    Prev
    Next
    INDEX
    Explanations

    每一次/几次

    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
     Ð
    0.65
     Д
    0.56
     Kxa
    0.55
     Ekonom
    0.55
     ऐसा
    0.55
     büy
    0.55
     Đ
    0.54
     Sí
    0.54
     Artículo
    0.54
    ách
    0.53
    POSITIVE LOGITS
    m
    0.68
    মানব
    0.62
    ation
    0.61
    data
    0.59
    ات
    0.58
     unus
    0.56
    db
    0.55
    location
    0.55
    рав
    0.54
    password
    0.54
    Activations Density 0.000%

    No Known Activations