© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50216
    Prev
    Next
    INDEX
    Explanations

    function definitions with comments

    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_31_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
     php
    0.37
     PHP
    0.37
     механиз
    0.30
     équip
    0.29
    PHP
    0.29
     mezzi
    0.29
    ENIX
    0.28
    冪
    0.28
     механи
    0.27
     Cron
    0.27
    POSITIVE LOGITS
    repo
    0.29
     December
    0.29
    cloud
    0.28
    itals
    0.28
    ren
    0.27
    Spark
    0.27
     lessons
    0.27
    Dec
    0.26
    >>()
    0.26
     repo
    0.26
    Activations Density 0.003%

    No Known Activations