© 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. 8978
    Prev
    Next
    INDEX
    Explanations

    URL path endings

    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
    𝑇
    1.60
    zelfde
    1.54
    𝐶
    1.54
    𝑛
    1.47
    الد
    1.47
    𝑘
    1.44
    𝑐
    1.41
    𝑁
    1.40
    𝑉
    1.40
    clause
    1.39
    POSITIVE LOGITS
    wości
    1.71
    ್‌
    1.61
    ์
    1.60
    t
    1.59
    ೇ
    1.55
     例文帳に追加
    1.55
    !\!\
    1.54
    raž
    1.54
    த
    1.52
     tarik
    1.49
    Activations Density 0.014%

    No Known Activations