© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57717
    Prev
    Next
    INDEX
    Explanations

    encouraged to

    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_11_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
    ри
    0.66
    Saw
    0.57
    o
    0.55
    果
    0.52
    ிர்
    0.52
    这
    0.51
    जा
    0.51
     Qualquer
    0.50
    сив
    0.50
     Sandoval
    0.50
    POSITIVE LOGITS
     biomarker
    0.50
    ArrowToggle
    0.49
     resellers
    0.49
     війни
    0.47
     yattha
    0.46
     uptick
    0.45
     +\
    0.45
    rapie
    0.45
    .$,
    0.45
     διάρκ
    0.45
    Activations Density 0.001%

    No Known Activations