© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46985
    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_13_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
    кугӀ
    0.54
     olímp
    0.51
     unico
    0.50
    ম
    0.50
    ้น
    0.50
     nhỏ
    0.50
    <unused996>
    0.50
     Mỹ
    0.50
    ن
    0.49
    Người
    0.49
    POSITIVE LOGITS
    ft
    0.52
     RT
    0.49
    ct
    0.49
     tonic
    0.49
    RT
    0.48
    rt
    0.48
    '
    0.47
    ,
    0.47
     standard
    0.46
    ret
    0.46
    Activations Density 0.000%

    No Known Activations