© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205253
    Prev
    Next
    INDEX
    Explanations

    code comments and file globs

    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_10_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
     и
    0.74
    ä
    0.70
     (
    0.68
    ।
    0.67
    !
    0.66
    wegian
    0.60
    ar
    0.59
    ale
    0.59
     και
    0.59
    rection
    0.59
    POSITIVE LOGITS
    다
    0.64
    ে
    0.64
    يّ
    0.62
    ेलकम
    0.61
    اگ
    0.57
    を目
    0.55
     raindrops
    0.55
    ாவில்
    0.55
    োডে
    0.54
    اا
    0.54
    Activations Density 0.000%

    No Known Activations