© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    text describing legal and national status and citizenship

    oai_token-act-pair · gemini-2.0-flash

    terms related to citizenship

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

    citizenship

    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
     out
    -0.56
     se
    -0.54
     vom
    -0.51
    tage
    -0.50
     mode
    -0.47
     изо
    -0.47
     squir
    -0.46
    endpush
    -0.46
    se
    -0.46
    出
    -0.45
    POSITIVE LOGITS
     citizens
    1.05
    citizens
    0.98
     citizen
    0.98
    Citizens
    0.95
     Citizens
    0.92
    citizen
    0.85
     Citizen
    0.84
     nationals
    0.82
     citizenship
    0.81
     citizenry
    0.80
    Activations Density 1.952%

    No Known Activations