© 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. 4117
    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
    ת
    2.91
    `${
    2.77
    ti
    2.55
    ate
    2.38
    дар
    2.32
    প
    2.32
     kwargs
    2.32
    st
    2.31
     Lagrangian
    2.29
    k
    2.28
    POSITIVE LOGITS
    పాటు
    2.71
    нений
    2.70
    ный
    2.58
     uwagi
    2.43
    いて
    2.38
    ুপ্ত
    2.33
    ваться
    2.32
     పాటు
    2.31
     dio
    2.31
    деги
    2.29
    Activations Density 0.027%

    No Known Activations