© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    more than just

    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
    я
    2.24
    й
    1.87
    o
    1.80
    ால்
    1.71
    quer
    1.61
    ยนต์
    1.60
    х
    1.59
    er
    1.57
     mezzo
    1.56
    стве
    1.55
    POSITIVE LOGITS
    tanggal
    2.03
    此之外
    1.78
     וכ
    1.61
    Tanggal
    1.59
    <bos>
    1.52
    ুন
    1.52
     që
    1.48
     وسهلا
    1.48
    ળો
    1.47
    ようだ
    1.46
    Activations Density 0.035%

    No Known Activations