© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15643
    Prev
    Next
    INDEX
    Explanations

    the phrase "a few" followed by a unit of measurement

    oai_token-act-pair · gemini-2.0-flash

    say "amount of time/distance"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.85
    some
    -0.85
    Some
    -0.73
     Some
    -0.71
     algum
    -0.66
     alguns
    -0.65
     algumas
    -0.63
     helft
    -0.62
     alguma
    -0.62
    一些
    -0.62
    POSITIVE LOGITS
     hundred
    0.73
     months
    0.65
     weeks
    0.65
     thousand
    0.62
     ویکی‌پدیای
    0.59
     tenths
    0.58
     dollars
    0.57
    hundred
    0.56
     hundert
    0.54
     autorytatywna
    0.53
    Activations Density 1.091%

    No Known Activations