© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3755
    Prev
    Next
    INDEX
    Explanations

    the ampersand character '&' and the word 'and'

    oai_token-act-pair · gemini-2.0-flash

    ampersands and related symbols

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

    &

    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
    ViewImports
    -0.77
     ivelany
    -0.72
     ligiloj
    -0.72
    principalTable
    -0.72
     ویکی‌پدی
    -0.71
    -------------</
    -0.71
     وتسجيلات
    -0.68
     crdi
    -0.68
    Datuak
    -0.68
     мәкал
    -0.67
    POSITIVE LOGITS
    amp
    1.54
     amp
    0.98
    Amp
    0.93
     Amp
    0.82
    quot
    0.79
    AMP
    0.78
    mdash
    0.73
    ndash
    0.69
    amps
    0.69
    c
    0.67
    Activations Density 1.706%

    No Known Activations