© 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. 3953
    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
    Not in Any Lists

    No Comments

    Negative Logits
     protruding
    1.29
     synaptic
    1.27
     восстановления
    1.20
    器
    1.19
     農
    1.17
    ган
    1.17
    ோம்
    1.16
     себя
    1.14
     vrt
    1.14
    不易
    1.12
    POSITIVE LOGITS
    ל
    1.20
    an
    1.19
    ್ಟ
    1.19
    ת
    1.17
    ا
    1.17
    त
    1.14
    ➢
    1.11
     बल्लेबाज
    1.07
    পাট
    1.06
     liens
    1.06
    Activations Density 0.017%

    No Known Activations