© 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. 15288
    Prev
    Next
    INDEX
    Explanations

    preguntar o tener dudas

    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
    Negative Logits
    ﭘ
    0.55
     Dharmendra
    0.54
    मिताभ
    0.52
    ﮐ
    0.52
     работе
    0.48
     खड़ी
    0.48
    комо
    0.48
    оте
    0.47
    qualiter
    0.46
    лли
    0.46
    POSITIVE LOGITS
     منع
    0.48
    Ao
    0.48
    Fishing
    0.47
    Print
    0.47
    The
    0.44
    Y
    0.42
    elines
    0.42
     שלא
    0.42
    epend
    0.41
     Acquisitions
    0.41
    Activations Density 0.000%

    No Known Activations