© 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. 8990
    Prev
    Next
    INDEX
    Explanations

    fraction notation in math

    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
    त
    0.66
    то
    0.63
    तें
    0.57
    ć
    0.53
    poss
    0.53
     bai
    0.52
    а
    0.51
    պես
    0.49
    pointed
    0.49
    pressed
    0.48
    POSITIVE LOGITS
    Eso
    0.57
     ஒரு
    0.56
     તેથી
    0.56
    ากหลาย
    0.55
    你
    0.54
    र
    0.54
    DING
    0.54
    靂
    0.54
     partir
    0.53
    i
    0.53
    Activations Density 0.040%

    No Known Activations