© 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. 40568
    Prev
    Next
    INDEX
    Explanations

    injury, leg, and BI

    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
    тім
    0.58
    o
    0.57
    ee
    0.57
    us
    0.55
     könnten
    0.54
    до
    0.53
    ίν
    0.52
     Wight
    0.52
    酒
    0.52
    fans
    0.52
    POSITIVE LOGITS
     जुलाई
    0.63
     ल
    0.58
     eduk
    0.56
     makalah
    0.55
     التعليم
    0.54
     рэ
    0.49
    ണു
    0.49
     Caj
    0.49
    Disponible
    0.49
     возникает
    0.49
    Activations Density 0.033%

    No Known Activations