© 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. 8976
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or symbols

    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
    ed
    1.44
    犸
    1.20
    oretically
    1.17
    y
    1.16
    weds
    1.16
    sters
    1.11
     ánimo
    1.08
    ='%
    1.08
    ernetes
    1.08
    mselves
    1.08
    POSITIVE LOGITS
    リ
    1.57
    CH
    1.42
     র
    1.40
    ⿺
    1.36
     की
    1.31
     bunyi
    1.31
     リ
    1.31
     ド
    1.27
    的大
    1.27
    anger
    1.25
    Activations Density 0.335%

    No Known Activations