© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141666
    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_0_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
    ش
    1.79
    ية
    1.77
    、
    1.68
    ő
    1.45
    ،
    1.37
    માં
    1.35
    يا
    1.34
    ，
    1.27
    특별시
    1.25
     Sử
    1.24
    POSITIVE LOGITS
    i
    1.66
    t
    1.65
    ר
    1.57
    e
    1.46
    o
    1.44
    .
    1.40
    ه
    1.40
    י
    1.38
    a
    1.38
    ت
    1.37
    Activations Density 0.000%

    No Known Activations