© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8270
    Prev
    Next
    INDEX
    Explanations

    words related to politics, especially elections and accusations of fraud

    oai_token-act-pair · gemini-2.0-flash

    Politics and Current events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.79
     cả
    -0.51
     Beyond
    -0.51
    kret
    -0.48
    AGER
    -0.48
    UED
    -0.47
    ÉM
    -0.47
    GRESS
    -0.47
     Note
    -0.47
     gab
    -0.46
    POSITIVE LOGITS
    <bos>
    1.17
    Personensuche
    0.93
     itſelf
    0.91
     Jefus
    0.88
     feroit
    0.87
     enfans
    0.84
    Aholisi
    0.84
     auffi
    0.83
    aarrggbb
    0.82
     ſche
    0.82
    Activations Density 4.849%

    No Known Activations