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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5617
    Prev
    Next
    INDEX
    Explanations

    just before

    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
    ,$$
    0.70
    ु
    0.69
    ும்
    0.66
    ти
    0.66
    ясь
    0.63
    ing
    0.63
    うえ
    0.63
    xception
    0.63
     mellitus
    0.61
    ुसार
    0.60
    POSITIVE LOGITS
    $('.
    0.85
    ers
    0.74
    $(".
    0.69
    л
    0.67
    ਰ
    0.66
    bhp
    0.65
    лля
    0.65
    upiter
    0.63
    ER
    0.62
    ル
    0.61
    Activations Density 0.003%

    No Known Activations