© 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. 9187
    Prev
    Next
    INDEX
    Explanations

    1922

    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
    櫚
    2.37
    ん
    2.34
    itary
    2.29
     wisata
    2.26
     Gł
    2.21
    jeno
    2.20
    งาม
    2.19
    в
    2.17
    پار
    2.17
    يرا
    2.17
    POSITIVE LOGITS
     denominators
    3.12
     Promenade
    2.54
     fact
    2.45
    //*
    2.34
    时候
    2.34
    {\
    2.32
     nga
    2.31
    csc
    2.29
     denominator
    2.27
     fluence
    2.25
    Activations Density 0.003%

    No Known Activations