© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6994
    Prev
    Next
    INDEX
    Explanations

    large language models

    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
    s
    1.94
    y
    1.70
    날
    1.69
    ج
    1.59
    ![
    1.58
    оборот
    1.44
    strcmp
    1.42
    เรื่อง
    1.41
    ve
    1.38
    டித்த
    1.36
    POSITIVE LOGITS
    苄
    1.91
     adrenal
    1.71
     correspondents
    1.67
     sj
    1.63
    р
    1.63
     hyphen
    1.62
    ergic
    1.59
     cât
    1.58
     Provisional
    1.54
    Ví
    1.54
    Activations Density 0.011%

    No Known Activations