© 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. 4289
    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
     naud
    2.09
    ма
    2.02
    ため
    2.00
    佬
    2.00
     CryptoJS
    1.99
    oos
    1.98
     prerequisite
    1.97
     squir
    1.97
    ),]),
    1.96
    कृत
    1.95
    POSITIVE LOGITS
    å
    2.17
    ά
    2.03
    ів
    1.92
     sinnv
    1.91
    g
    1.86
    j
    1.79
    u
    1.75
    ύν
    1.75
    های
    1.74
     som
    1.71
    Activations Density 0.028%

    No Known Activations