© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81884
    Prev
    Next
    INDEX
    Explanations

    已关闭, 故宫

    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_0_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
    ك
    1.81
    д
    1.77
    ة
    1.62
    ве
    1.54
     لیګ
    1.52
    يان
    1.52
    يا
    1.46
     هاي
    1.44
    كين
    1.41
     براي
    1.41
    POSITIVE LOGITS
    ↵
    2.23
    .
    1.88
    -
    1.73
    ر
    1.62
    O
    1.61
    4
    1.59
    its
    1.52
    im
    1.49
     an
    1.48
    (
    1.44
    Activations Density 0.000%

    No Known Activations