© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    plasma cells, donation, and chlamydia

    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
    ${
    3.62
    ве
    2.84
    ্ড
    2.30
    gitian
    2.29
    ज
    2.26
     معي
    2.19
    ViewModels
    2.17
    `${
    2.15
    וא
    2.14
    கை
    2.10
    POSITIVE LOGITS
    𝐭
    3.26
    𝐝
    3.14
    𝐢
    3.06
    𝘥
    3.00
    𝐮
    2.94
    𝐛
    2.90
     armas
    2.88
    ına
    2.85
    𝐬
    2.85
     ResultSet
    2.74
    Activations Density 0.018%

    No Known Activations