© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2590
    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_12_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obliged
    0.45
    k
    0.43
    bodies
    0.42
    g
    0.42
    ber
    0.42
    ena
    0.41
    b
    0.38
    L
    0.38
    虐
    0.37
     cook
    0.37
    POSITIVE LOGITS
     Strategy
    0.67
     我的
    0.62
     Inoltre
    0.62
     Правда
    0.61
    戤
    0.61
     Synchronization
    0.61
     Horizonte
    0.59
     Notas
    0.58
     Perhaps
    0.58
    SalesReport
    0.58
    Activations Density 0.118%

    No Known Activations