© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1589
    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
    y
    1.54
    д
    1.31
    u
    1.27
    ^{
    1.19
    د
    1.11
    vať
    1.09
     erst
    1.08
     사항
    1.06
    л
    1.05
    ^{-}$
    1.01
    POSITIVE LOGITS
     सप्त
    1.08
    ק
    1.07
    ਿਰ
    1.07
     bleue
    0.99
    ಕ
    0.98
     تعالى
    0.97
    ಕ್
    0.96
     accuse
    0.94
     vse
    0.94
    你
    0.94
    Activations Density 0.025%

    No Known Activations