© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204761
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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_25_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
     worse
    0.37
    要知道
    0.34
     lobby
    0.33
    \|^
    0.33
     LinkedIn
    0.32
     bellow
    0.32
     Worse
    0.32
    ৩৯
    0.32
     reload
    0.31
     เอง
    0.31
    POSITIVE LOGITS
    ProductsStore
    0.37
    грам
    0.37
    ʐ
    0.37
    ktan
    0.35
    Ple
    0.35
    chang
    0.35
     шла
    0.34
    PLE
    0.33
    MACl
    0.33
    pian
    0.32
    Activations Density 0.002%

    No Known Activations