© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242204
    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_25_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
    odiac
    0.49
    án
    0.46
    agog
    0.44
     宋
    0.43
     Singh
    0.42
    igrams
    0.41
    file
    0.41
    oids
    0.40
    atique
    0.40
    izarre
    0.40
    POSITIVE LOGITS
     safer
    0.54
    ダ
    0.53
    ോട്ടോ
    0.47
     ترك
    0.47
     ځای
    0.47
     закона
    0.47
    Cas
    0.46
    İN
    0.46
     Saf
    0.46
     약
    0.46
    Activations Density 0.000%

    No Known Activations