© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4191
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     adjoint
    2.87
    speople
    2.87
    nych
    2.77
    pq
    2.74
    larla
    2.73
    punt
    2.70
    UserDefaults
    2.69
    k
    2.67
    க
    2.63
    ਲ
    2.59
    POSITIVE LOGITS
     дела
    3.00
    𝗗
    2.57
    چ
    2.53
     notamment
    2.52
     iler
    2.49
     montaña
    2.42
    𝘁
    2.39
    𝟰
    2.36
    гө
    2.32
    این
    2.27
    Activations Density 0.034%

    No Known Activations