© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145339
    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     k
    0.48
     ziemlich
    0.45
     ক
    0.45
     Following
    0.44
     %
    0.43
     、
    0.41
     হতে
    0.40
     –
    0.40
     By
    0.40
     to
    0.40
    POSITIVE LOGITS
    тят
    0.61
    нди
    0.55
     прошу
    0.54
     общества
    0.53
    л
    0.52
    зова
    0.51
    estruct
    0.50
    кала
    0.50
    спользова
    0.48
     trycatch
    0.48
    Activations Density 0.000%

    No Known Activations