© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13442
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to politics, history, and government

    oai_token-act-pair · gemini-2.0-flash

    Political figures and events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     king
    -0.85
     governor
    -0.80
     director
    -0.77
     Governor
    -0.75
     Director
    -0.74
    Governor
    -0.73
     president
    -0.73
     Directors
    -0.72
     directors
    -0.72
    governor
    -0.71
    POSITIVE LOGITS
     للاسماء
    0.59
     employee
    0.59
    Jeografia
    0.57
    participant
    0.57
    czaj
    0.56
     participant
    0.55
     pop
    0.55
     Pop
    0.54
     worker
    0.54
     viewer
    0.54
    Activations Density 3.902%

    No Known Activations