© 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. 4007
    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
     tacit
    1.56
    Analysts
    1.56
     tiên
    1.50
    ড
    1.49
     Overland
    1.43
     проведения
    1.40
    PerformLayout
    1.39
    <!---
    1.39
    Needless
    1.37
    റ്റ്
    1.37
    POSITIVE LOGITS
    at
    2.05
    ת
    1.85
    in
    1.77
    ла
    1.71
    ي
    1.65
    ان
    1.60
    an
    1.59
    elä
    1.54
    ТЕ
    1.53
    ლი
    1.52
    Activations Density 0.075%

    No Known Activations