© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 273
    Prev
    Next
    INDEX
    Explanations

    contexts mentioning ethnicity or national origin

    oai_token-act-pair · gemini-2.0-flash

    nationalities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     colonial
    -0.80
    Colonial
    -0.76
    colonial
    -0.76
    colony
    -0.75
     Colonial
    -0.75
    lawayo
    -0.64
    homonymie
    -0.64
     BorderRadius
    -0.61
    Colony
    -0.60
     kolon
    -0.59
    POSITIVE LOGITS
     Italian
    0.84
     European
    0.78
     German
    0.76
     Italians
    0.76
     Japanese
    0.76
     italianos
    0.75
    Italian
    0.73
     Scottish
    0.73
    German
    0.73
     Swedish
    0.73
    Activations Density 2.735%

    No Known Activations