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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15366
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially cities and regions

    oai_token-act-pair · gemini-2.0-flash

    various locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     الحره
    -0.56
    AddHtmlAttribute
    -0.52
     vapa
    -0.50
    ReusableCell
    -0.48
    toarele
    -0.47
    cuela
    -0.47
     isInitialized
    -0.46
    croll
    -0.46
     للاسماء
    -0.46
    :✨
    -0.45
    POSITIVE LOGITS
    ConverterFactory
    0.64
     Andorra
    0.63
    
    0.63
    acabana
    0.63
    upaten
    0.62
     Guam
    0.61
     Connecticut
    0.61
     Florida
    0.60
    OGND
    0.60
    Connecticut
    0.59
    Activations Density 8.380%

    No Known Activations