© 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. 3475
    Prev
    Next
    INDEX
    Explanations

    peace and quiet

    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
    re
    1.01
     loser
    0.88
    !--
    0.85
    ússia
    0.84
    प
    0.82
     dirt
    0.82
     الخام
    0.81
    🧀
    0.81
    Após
    0.81
     discapac
    0.80
    POSITIVE LOGITS
     lặng
    1.19
    謐
    1.06
    谧
    1.00
     demeanor
    0.98
    ato
    0.96
     سازی
    0.93
     terjadinya
    0.91
    स्त्री
    0.91
    ที่สุด
    0.87
    ти
    0.87
    Activations Density 0.148%

    No Known Activations