© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14427
    Prev
    Next
    INDEX
    Explanations

    references to the United States and other countries

    oai_token-act-pair · gemini-2.0-flash

    United

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     United
    -1.34
    United
    -1.25
     UNITED
    -1.09
    UNITED
    -0.99
     united
    -0.98
    united
    -0.97
     Vereinigten
    -0.77
     Utd
    -0.77
    arXiv
    -0.61
     Verenigde
    -0.61
    POSITIVE LOGITS
    SourceChecksum
    0.67
    êmios
    0.61
    nsito
    0.60
     архивлан
    0.60
     disambiguazione
    0.59
     kasarigan
    0.59
    middels
    0.56
    Seznam
    0.56
     Peabody
    0.56
     offerts
    0.56
    Activations Density 13.456%

    No Known Activations