© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    test function names

    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
    𝘵
    1.44
    deterministic
    1.32
    𝙠
    1.29
     Skywalker
    1.29
    actions
    1.28
    tired
    1.28
     começ
    1.28
    
    1.26
    IA
    1.26
    ت
    1.25
    POSITIVE LOGITS
    з
    1.15
     counters
    1.15
    Основ
    1.12
    И
    1.10
     gleichen
    1.09
     bestimmt
    1.08
    Это
    1.06
    Вы
    1.06
     possibile
    1.05
    Что
    1.05
    Activations Density 0.002%

    No Known Activations