© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4789
    Prev
    Next
    INDEX
    Explanations

    references to people of the United states, or the American people

    oai_token-act-pair · gemini-2.0-flash

    terms related to groups of people

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

    Human populations

    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
     society
    -0.68
    society
    -0.60
    Society
    -0.54
     gynhyrchwyd
    -0.52
     nueces
    -0.52
    sizeCache
    -0.50
     Society
    -0.50
    canestro
    -0.50
    neté
    -0.47
     SOCIETY
    -0.46
    POSITIVE LOGITS
     electorate
    0.91
     community
    0.91
     population
    0.83
     populace
    0.79
     workforce
    0.74
     fanbase
    0.71
    community
    0.69
     universe
    0.69
     POPULATION
    0.68
     communauté
    0.68
    Activations Density 2.780%

    No Known Activations