© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102920
    Prev
    Next
    INDEX
    Explanations

    bursts in or rushes

    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_14_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
    ل
    0.42
    ζ
    0.40
     joints
    0.39
    </strong>
    0.39
    ع
    0.39
    مق
    0.38
    èvre
    0.37
    짰
    0.37
     Eastern
    0.37
    okhlov
    0.37
    POSITIVE LOGITS
     lä
    0.47
    ından
    0.46
    tiin
    0.43
    larını
    0.43
     сама
    0.42
     indip
    0.41
    ları
    0.40
    t
    0.40
     bö
    0.40
     estarán
    0.40
    Activations Density 0.004%

    No Known Activations