© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76887
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     Theres
    0.42
     Chiu
    0.41
     coup
    0.40
     Colson
    0.40
    FIA
    0.38
     tỏ
    0.38
     isnt
    0.38
    }')
    0.37
    allax
    0.37
     cuy
    0.37
    POSITIVE LOGITS
    ⾏
    0.37
     американский
    0.35
    वणी
    0.35
     без
    0.35
    百度
    0.34
     времен
    0.34
    Без
    0.34
     বৃত্ত
    0.34
     تؤ
    0.34
     Routed
    0.33
    Activations Density 0.000%

    No Known Activations