© 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. 46992
    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
     Primeiro
    0.55
    缉
    0.55
    రీలు
    0.52
    我們
    0.51
     Großbritannien
    0.50
     Menzies
    0.50
    ט
    0.50
     Polsce
    0.49
     দৈত্য
    0.48
    澳大利亚
    0.48
    POSITIVE LOGITS
     air
    0.57
     has
    0.52
     panel
    0.51
     setting
    0.49
     gas
    0.48
     can
    0.48
     coolant
    0.46
     f
    0.46
     loved
    0.46
     and
    0.44
    Activations Density 0.000%

    No Known Activations