© 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. 4184
    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
    ع
    2.68
     tions
    2.37
    abh
    2.29
     tion
    2.26
    نة
    2.25
    ส์
    2.23
    tion
    2.08
    igned
    2.03
    ^*
    1.98
    别的
    1.96
    POSITIVE LOGITS
     comforted
    2.93
     retorted
    2.80
     governed
    2.73
     dictated
    2.71
     dared
    2.70
     purified
    2.70
     immobilier
    2.59
     risen
    2.49
     léger
    2.42
     suited
    2.42
    Activations Density 0.002%

    No Known Activations