© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41375
    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_22_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
     পর্দা
    0.39
    hest
    0.39
    こ
    0.38
    eg
    0.38
    ing
    0.37
    iya
    0.36
    egang
    0.36
    egas
    0.36
     এমন
    0.35
     Exceptions
    0.35
    POSITIVE LOGITS
    ്ല
    0.38
    нэт
    0.38
     pembuatan
    0.38
    assung
    0.38
     lectores
    0.37
     ordenada
    0.37
    GeneratedValue
    0.36
    CreateTable
    0.35
    衲
    0.35
     directa
    0.35
    Activations Density 0.000%

    No Known Activations