© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1803
    Prev
    Next
    INDEX
    Explanations

    JetBrains IDEs like IntelliJ IDEA / PyCharm

    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_39_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
    鹑
    0.40
    复杂
    0.40
     복
    0.39
    SqlServer
    0.39
    複雜
    0.39
    σωπ
    0.38
    ﱢ
    0.38
    逘
    0.38
     сложные
    0.38
    뎁
    0.38
    POSITIVE LOGITS
    JT
    0.37
     عند
    0.36
     Jessie
    0.36
     クラ
    0.35
     groupe
    0.35
    봉
    0.35
     platform
    0.34
     Angela
    0.34
     رف
    0.34
     插
    0.34
    Activations Density 0.004%

    No Known Activations