© 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. 5296
    Prev
    Next
    INDEX
    Explanations

    said in or said,

    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
     PartialEq
    1.70
    χαν
    1.58
    ❼
    1.43
    是一些
    1.37
    빵
    1.34
     тысяч
    1.33
    getic
    1.33
     Hinweis
    1.32
     Warsz
    1.29
    các
    1.28
    POSITIVE LOGITS
    ज
    1.76
    ہار
    1.53
    东西
    1.41
    Hmmm
    1.41
    '_
    1.41
    লা
    1.41
    ',$
    1.39
    estructive
    1.39
    ்
    1.38
    横浜
    1.37
    Activations Density 0.006%

    No Known Activations