© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88793
    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_11_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
     dalla
    0.57
     discouraged
    0.55
     berücksichtigt
    0.54
     philanthropist
    0.53
    在一
    0.52
    ស
    0.52
     universitaria
    0.52
     sanitaria
    0.52
     sowie
    0.51
     unto
    0.50
    POSITIVE LOGITS
     什么
    0.53
     répar
    0.52
    Offsets
    0.51
    오
    0.50
     對
    0.50
    _
    0.49
    여러
    0.48
    오는
    0.48
    蚵
    0.47
    보고
    0.47
    Activations Density 0.000%

    No Known Activations