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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3199
    Prev
    Next
    INDEX
    Explanations

    function definition

    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_5_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
    ใช้งาน
    0.47
    iť
    0.45
    Deja
    0.45
    rss
    0.45
    দের
    0.45
    setwd
    0.45
    𝘃
    0.45
    𝗷
    0.45
    rd
    0.45
    ра
    0.44
    POSITIVE LOGITS
    у
    0.59
    果た
    0.54
    ும்
    0.53
    kraft
    0.48
    ing
    0.48
    лоти
    0.47
    не
    0.45
    ти
    0.45
    തന്ത്ര
    0.44
    <bos>
    0.43
    Activations Density 0.339%

    No Known Activations