© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46903
    Prev
    Next
    INDEX
    Explanations

    upload and progress

    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_13_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
    স
    0.47
    స్‌
    0.45
    »،
    0.45
    applying
    0.44
    原
    0.44
    FOM
    0.44
    ০
    0.43
    시
    0.43
    aksanaan
    0.43
    ف
    0.43
    POSITIVE LOGITS
     වර්ග
    0.54
    ANDE
    0.51
     Ă
    0.51
    नेटरी
    0.50
     វា
    0.48
     තා
    0.48
    ็ค
    0.48
     نجي
    0.48
     appease
    0.47
    唓
    0.47
    Activations Density 0.029%

    No Known Activations