© 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. 2221
    Prev
    Next
    INDEX
    Explanations

    C++ common libraries and CUDA

    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
     compile
    1.16
     compiled
    1.14
     Compile
    1.09
     C
    1.09
    编译
    1.03
     Compilation
    1.00
    compiled
    0.99
     compiling
    0.99
     compilation
    0.99
     Compiled
    0.99
    POSITIVE LOGITS
     economies
    0.40
    sbom
    0.37
     pharmacy
    0.37
    直
    0.36
     livestock
    0.35
    襲
    0.35
     workplace
    0.35
    herme
    0.35
     रीठा
    0.34
    획
    0.34
    Activations Density 0.076%

    No Known Activations