© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8855
    Prev
    Next
    INDEX
    Explanations

    dynamic-link libraries and window handles

    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_40_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
     Bà
    0.47
     change
    0.39
    tä
    0.39
     bà
    0.39
     Küchen
    0.39
    -<
    0.38
     irrig
    0.37
     Bah
    0.37
     substantially
    0.37
     `<
    0.37
    POSITIVE LOGITS
     DLL
    0.68
    DLL
    0.64
    Dll
    0.62
    dll
    0.62
     dll
    0.54
    EXE
    0.47
    DYNAMIC
    0.44
     EXE
    0.42
    dynamic
    0.42
     dinâmica
    0.42
    Activations Density 0.003%

    No Known Activations