© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254268
    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_56_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
     اك
    0.40
     আক
    0.39
     አንድ
    0.36
    ikale
    0.34
     acc
    0.34
    rakk
    0.33
    Lod
    0.33
    坊
    0.33
    薈
    0.33
    ्स
    0.33
    POSITIVE LOGITS
     ჰ
    0.42
     Cronin
    0.42
    lina
    0.41
    llr
    0.40
    adios
    0.40
     हु
    0.38
    िले
    0.38
    logos
    0.38
     postice
    0.38
     Tun
    0.37
    Activations Density 0.000%

    No Known Activations