© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221470
    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_31_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
     globale
    0.38
     telah
    0.38
    ≺
    0.38
    zzet
    0.38
    ammation
    0.37
     fabrik
    0.37
     menjadikan
    0.37
     hutan
    0.37
    PNG
    0.36
    buatan
    0.36
    POSITIVE LOGITS
     typewriter
    0.36
    ﮈ
    0.35
     Copeland
    0.35
     slightest
    0.34
     Exile
    0.34
     Seymour
    0.34
    ಬ್
    0.34
    研究生
    0.34
     Holy
    0.33
     Dodge
    0.33
    Activations Density 0.000%

    No Known Activations