© 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. 5222
    Prev
    Next
    INDEX
    Explanations

    sets the scene or stage

    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
    
    2.59
    lık
    2.48
    ן
    2.38
    あります
    2.28
     inversely
    2.21
    ето
    2.14
    iteli
    2.12
     sağlan
    2.12
    
    2.12
    או
    2.11
    POSITIVE LOGITS
    िंग्स
    3.96
    TING
    2.93
    к
    2.92
    idaknya
    2.68
    to
    2.57
    它
    2.45
    ts
    2.45
    uation
    2.43
    tting
    2.41
    ძლიათ
    2.36
    Activations Density 0.100%

    No Known Activations