© 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. 4268
    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
    ed
    2.89
    sama
    2.35
    skim
    2.32
    ة
    2.30
    ित
    2.25
    sum
    2.18
    she
    2.12
    suites
    2.07
    nrow
    2.06
    st
    2.05
    POSITIVE LOGITS
    ра
    2.49
    ^{-}
    2.42
     možnost
    2.40
     abl
    2.40
     alors
    2.39
     cinqu
    2.38
    ாட்ட
    2.36
    辋
    2.36
     '?
    2.32
    ल
    2.31
    Activations Density 0.003%

    No Known Activations