© 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. 8702
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    𝐵
    4.29
    𝐼
    4.13
    𝑀
    4.09
    𝑁
    3.92
    𝐸
    3.92
    𝑒
    3.87
    𝑇
    3.81
    𝑢
    3.67
    𝑡
    3.67
    𝑃
    3.66
    POSITIVE LOGITS
    ে
    3.70
    ך
    3.22
    d
    3.04
    ها
    2.94
    ್‌
    2.88
    ek
    2.71
    ك
    2.71
    েবের
    2.67
    "\
    2.67
    も
    2.66
    Activations Density 0.248%

    No Known Activations