© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10092
    Prev
    Next
    INDEX
    Explanations

    mentions of the president of the united states, particularly Obama and Trump, and political terms

    oai_token-act-pair · gemini-2.0-flash

    US presidents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    setupUi
    -0.50
    verifyException
    -0.49
    ức
    -0.48
    heta
    -0.45
    :+:
    -0.42
    ieuses
    -0.42
    GraphicsUnit
    -0.41
    InstanceState
    -0.41
     MainAxisSize
    -0.41
    twimg
    -0.41
    POSITIVE LOGITS
     Trump
    1.42
     Barack
    1.29
     Obama
    1.29
    Trump
    1.27
     Bush
    1.20
     Donald
    1.18
     President
    1.16
     Biden
    1.14
    Bush
    1.13
    Obama
    1.09
    Activations Density 1.790%

    No Known Activations