© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35903
    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_7_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
     at
    0.87
     of
    0.77
    ma
    0.67
     за
    0.62
     from
    0.61
    ley
    0.61
    ás
    0.61
    nder
    0.61
    中
    0.60
     a
    0.60
    POSITIVE LOGITS
    The
    0.94
     kullanımı
    0.80
    و
    0.77
    این
    0.71
    ت
    0.71
    on
    0.70
     همچنین
    0.67
    This
    0.66
    を使って
    0.66
     Almanya
    0.64
    Activations Density 0.000%

    No Known Activations