© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8615
    Prev
    Next
    INDEX
    Explanations

    in the end

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ‍
    2.54
    ي
    2.53
    𝗜
    2.52
    ल
    2.47
    ilin
    2.46
    ्त
    2.45
    AUG
    2.32
     особенности
    2.30
    ilidad
    2.30
    тни
    2.28
    POSITIVE LOGITS
    s
    2.54
    هایت
    2.31
    aparte
    2.26
    য়ের
    2.23
    辙
    2.21
    tedir
    2.21
    ের
    2.19
    '')
    2.17
     incomes
    2.15
    olecules
    2.14
    Activations Density 0.001%

    No Known Activations