© 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. 61638
    Prev
    Next
    INDEX
    Explanations

    performance-critical applications

    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
    fut
    0.56
    Reilly
    0.54
     hourglass
    0.54
    ພາ
    0.54
    Leftrightarrow
    0.54
    ﺔ
    0.53
    ស្ថានភាព
    0.53
     cloth
    0.52
     roul
    0.52
     murderous
    0.51
    POSITIVE LOGITS
    В
    0.57
     YOU
    0.55
    в
    0.55
     बोलते
    0.54
    ح
    0.54
     Pareto
    0.54
    И
    0.53
    A
    0.52
     เลือก
    0.50
     Elmer
    0.50
    Activations Density 0.001%

    No Known Activations