© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129139
    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_6_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
    a
    1.19
    o
    1.09
    in
    1.09
    an
    1.02
    i
    0.94
    at
    0.91
    n
    0.91
    from
    0.88
    that
    0.87
    u
    0.85
    POSITIVE LOGITS
    것
    0.85
     modelos
    0.83
     positivos
    0.81
     anuncios
    0.77
     artículos
    0.74
     ejemplos
    0.73
     edificios
    0.73
     coches
    0.73
     anúncios
    0.73
     restaurantes
    0.71
    Activations Density 0.000%

    No Known Activations