© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45664
    Prev
    Next
    INDEX
    Explanations

    code parsing operations

    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_22_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
    جنة
    0.24
    Ви
    0.23
    виа
    0.23
    ract
    0.23
    erie
    0.22
    mett
    0.22
     =>
    0.22
    Command
    0.21
    Car
    0.21
    ッチ
    0.21
    POSITIVE LOGITS
     crevices
    0.27
     அரங்க
    0.26
    洵
    0.25
     exasper
    0.25
     проце
    0.25
     closures
    0.25
     жа
    0.24
     المثلثيه
    0.24
     निर्धारण
    0.24
     saranam
    0.24
    Activations Density 0.019%

    No Known Activations