© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33223
    Prev
    Next
    INDEX
    Explanations

    map and apply function

    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
     slits
    0.43
    ствии
    0.43
    ު
    0.38
     درج
    0.37
     eficiente
    0.37
    ثمار
    0.37
     substitute
    0.37
    逕
    0.36
    ക്ത
    0.36
     মহিলার
    0.36
    POSITIVE LOGITS
     FUNCTION
    0.45
    function
    0.44
     function
    0.44
     இட
    0.37
    Quit
    0.37
    quit
    0.37
    QUIT
    0.36
    raad
    0.35
     Function
    0.35
    函数
    0.35
    Activations Density 0.005%

    No Known Activations