© 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. 17784
    Prev
    Next
    INDEX
    Explanations

    function definition and arguments

    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
     দিল্লির
    0.41
    джа
    0.39
    ıldığı
    0.39
     Misc
    0.37
     Aristotle
    0.35
    ılığı
    0.35
    OOSE
    0.35
    删
    0.35
     Gir
    0.35
     দিল্লিতে
    0.34
    POSITIVE LOGITS
     dining
    0.48
    Nun
    0.39
    Dining
    0.39
     Dining
    0.38
    dining
    0.38
    看護
    0.38
     المش
    0.38
     सूर्
    0.36
    [*]
    0.36
    lasma
    0.36
    Activations Density 0.060%

    No Known Activations