© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83189
    Prev
    Next
    INDEX
    Explanations

    sync, 顶配

    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
    س
    1.82
    out
    1.37
    od
    1.34
    og
    1.31
     he
    1.30
    1
    1.23
    h
    1.22
    c
    1.22
    ،
    1.20
    ast
    1.18
    POSITIVE LOGITS
    ла
    1.69
    л
    1.61
    لية
    1.45
    ין
    1.45
    ה
    1.41
    տ
    1.41
    т
    1.38
    ческие
    1.34
    رى
    1.34
    مي
    1.30
    Activations Density 0.000%

    No Known Activations