© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11892
    Prev
    Next
    INDEX
    Explanations

    function main declaration

    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
    Kel
    0.39
    Monkey
    0.36
    Og
    0.34
    нора
    0.34
     మ‌
    0.34
    書き
    0.33
     تكتب
    0.33
    𝚌
    0.33
    wra
    0.32
    Ald
    0.32
    POSITIVE LOGITS
    的主要
    1.02
     main
    1.02
    主な
    0.87
     основным
    0.86
     hlavní
    0.85
    main
    0.84
     glavni
    0.83
     главной
    0.83
     utama
    0.82
     principale
    0.80
    Activations Density 0.010%

    No Known Activations