© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3675
    Prev
    Next
    INDEX
    Explanations

    Ryzen 7000/8000 series

    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
    ுள்ளார்
    1.60
    essay
    1.52
    er
    1.50
    financed
    1.47
    ER
    1.44
    ┏
    1.40
    izing
    1.40
    []{
    1.37
    ''}
    1.32
    elephant
    1.31
    POSITIVE LOGITS
    畢
    1.70
    দের
    1.66
    ր
    1.58
    ת
    1.51
    การ
    1.50
     gemidd
    1.49
     lượng
    1.48
    のは
    1.46
    ち
    1.44
    avier
    1.44
    Activations Density 0.000%

    No Known Activations