© 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. 8555
    Prev
    Next
    INDEX
    Explanations

    despair, odds

    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
     resonate
    0.54
     recher
    0.49
    тся
    0.47
     wealth
    0.46
     guilty
    0.46
     suite
    0.46
     rechts
    0.45
     yield
    0.45
    [
    0.45
     suites
    0.44
    POSITIVE LOGITS
    org
    0.62
     Adidas
    0.61
     Istanbul
    0.59
    uk
    0.57
    inim
    0.57
    or
    0.57
     ພວກເຮົາ
    0.57
    oil
    0.57
    úr
    0.57
     Bangkok
    0.56
    Activations Density 0.037%

    No Known Activations