© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256307
    Prev
    Next
    INDEX
    Explanations

    feature structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     فرنسا
    0.43
    ření
    0.41
    husband
    0.41
    ják
    0.40
    China
    0.40
     Uyg
    0.40
    فیر
    0.39
    雞
    0.38
    ículas
    0.38
    。[
    0.38
    POSITIVE LOGITS
     पश्चात
    0.34
     proclam
    0.33
     план
    0.33
    ంటి
    0.33
     toi
    0.32
     misdemeanor
    0.32
     Dissertation
    0.32
     احتجاج
    0.32
     mia
    0.32
     announcements
    0.32
    Activations Density 0.000%

    No Known Activations