© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    quotes in articles, especially those from politicians

    oai_token-act-pair · gemini-2.0-flash

    words related to politics or government entities

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

    News, politics and government

    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
    DoubleQuotes
    -0.57
    SourceChecksum
    -0.54
    LEncoder
    -0.53
    EndInit
    -0.50
     fidé
    -0.48
     fréquent
    -0.46
     supérieure
    -0.45
    Архівовано
    -0.43
    cuentes
    -0.43
    __*/
    -0.42
    POSITIVE LOGITS
     Weiner
    0.66
     Labour
    0.63
     Италијани
    0.59
    jectures
    0.56
    Escrit
    0.56
     kasarigan
    0.55
     independence
    0.55
     MPs
    0.54
    plots
    0.54
     applause
    0.54
    Activations Density 6.961%

    No Known Activations