© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25616
    Prev
    Next
    INDEX
    Explanations

    synonymy, clause, parents, Mendeleev, him, tips, currently

    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_10_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
    тай
    0.50
    timeInterval
    0.50
    ทีม
    0.48
     संग्रहालय
    0.47
     کاشت
    0.47
    subseteq
    0.46
     화
    0.46
    های
    0.45
    ผู้ชมในสนาม
    0.45
     Ünivers
    0.45
    POSITIVE LOGITS
    ă
    0.52
     adds
    0.45
     insures
    0.44
    <
    0.44
    edly
    0.42
     શા
    0.42
     indecent
    0.42
     unfolds
    0.42
     alguns
    0.42
    <>();
    0.42
    Activations Density 0.000%

    No Known Activations