© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9237
    Prev
    Next
    INDEX
    Explanations

    name followed by a special token

    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_3_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
    ively
    2.97
    %>
    2.72
     Başkan
    2.47
    িতে
    2.45
    %%
    2.41
    ^[
    2.40
     Surely
    2.37
    tyn
    2.36
     summoned
    2.35
     affixed
    2.33
    POSITIVE LOGITS
    en
    3.99
    те
    3.69
    as
    3.14
     whis
    2.50
    ார்
    2.45
    메라
    2.37
    다
    2.32
    ਦਰ
    2.27
    ia
    2.26
     vicino
    2.25
    Activations Density 0.004%

    No Known Activations