© 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. 27614
    Prev
    Next
    INDEX
    Explanations

    function 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
    榈
    0.40
    흥
    0.39
    썬
    0.38
    ೋನ್
    0.37
    არგ
    0.37
    ugd
    0.37
     दृष्टी
    0.37
     "";
    0.36
    UX
    0.36
     sprays
    0.36
    POSITIVE LOGITS
     điểm
    0.40
    点の
    0.40
    dde
    0.39
    点が
    0.39
     Iterate
    0.38
    ïque
    0.38
     intentional
    0.35
     ሰ
    0.35
     accurate
    0.35
    +[
    0.34
    Activations Density 0.002%

    No Known Activations