© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88607
    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_11_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
    ară
    0.57
    குழந்த
    0.56
    hydrocèle
    0.55
    <unused616>
    0.53
    îne
    0.52
    ㄶ
    0.52
    <unused1868>
    0.52
    ñal
    0.52
    靘
    0.51
     নিহত
    0.51
    POSITIVE LOGITS
     (
    0.57
      
    0.50
     rem
    0.46
    ,
    0.44
    Determine
    0.43
    )
    0.43
     on
    0.43
    US
    0.43
    U
    0.42
     revenues
    0.42
    Activations Density 0.000%

    No Known Activations