© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5659
    Prev
    Next
    INDEX
    Explanations

    references to China and current events/news

    oai_token-act-pair · gemini-2.0-flash

    mentions of "Chinese" or related terms

    np_token-act-pair-logits · gpt-4o-mini

    Chinese/China

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.67
     '\\;'
    -0.56
    AlterField
    -0.55
     nahilalakip
    -0.55
    ChildScrollView
    -0.54
    posedge
    -0.53
    ArrowToggle
    -0.50
    setHorizontal
    -0.49
    
    -0.49
    Gambas
    -0.49
    POSITIVE LOGITS
     propOrder
    0.69
    Китай
    0.64
     astore
    0.62
     Chinese
    0.61
     China
    0.58
     chinoise
    0.55
    Chinese
    0.53
    IntoConstraints
    0.51
    China
    0.48
    hikari
    0.48
    Activations Density 5.121%

    No Known Activations