© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85207
    Prev
    Next
    INDEX
    Explanations

    rect()

    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_18_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
     atan
    0.50
    瑉
    0.48
     yal
    0.48
     mediterranean
    0.48
     olhar
    0.48
    ্্র
    0.48
     spes
    0.46
    ं
    0.46
     CHAIRMAN
    0.46
     javafx
    0.46
    POSITIVE LOGITS
    비
    0.47
     полного
    0.47
    シティ
    0.44
     Tests
    0.43
     इंच
    0.42
    ServiceImpl
    0.42
    bigcirc
    0.42
    引进
    0.41
    Detroit
    0.39
     हिस्सा
    0.39
    Activations Density 0.000%

    No Known Activations