© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143988
    Prev
    Next
    INDEX
    Explanations

    большой; увеличение

    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
    1.80
    ן
    1.54
    ке
    1.46
    ુ
    1.30
    он
    1.27
    기
    1.23
    the
    1.20
    ন
    1.20
    да
    1.18
    ش
    1.16
    POSITIVE LOGITS
    ים
    2.00
    s
    1.77
    ی
    1.75
     to
    1.71
    ä
    1.67
    ς
    1.49
    一
    1.40
    y
    1.38
     are
    1.34
    ことを
    1.29
    Activations Density 0.001%

    No Known Activations