© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83977
    Prev
    Next
    INDEX
    Explanations

    header=true

    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_23_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
     Beige
    0.47
    veda
    0.46
     beige
    0.45
     architect
    0.44
    zd
    0.42
     glue
    0.42
    ament
    0.41
     kat
    0.41
     moustache
    0.40
    涤
    0.40
    POSITIVE LOGITS
     toneladas
    0.46
     秒
    0.43
    Laravel
    0.42
     सोचा
    0.41
     λειτουργ
    0.40
    తర
    0.39
    крема
    0.38
    他の
    0.37
    साम
    0.37
    优化
    0.37
    Activations Density 0.001%

    No Known Activations