© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8409
    Prev
    Next
    INDEX
    Explanations

    technical or jargonistic terms that are specific to certain fields.

    oai_token-act-pair · gemini-2.0-flash

    stopwords Method used: 3 — TOP_POSITIVE_LOGITS are common stopwords — stopwords

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    GEBURTSDATUM
    -0.95
     nakalista
    -0.86
    ↵
    -0.81
     AssemblyCulture
    -0.80
    <bos>
    -0.79
    verwijspagina
    -0.75
    WebElementEntity
    -0.75
    setVerticalGroup
    -0.74
     <",
    -0.73
    ʺ
    -0.73
    POSITIVE LOGITS
     the
    1.42
     a
    1.01
     and
    1.00
     it
    0.98
     as
    0.96
     both
    0.95
     all
    0.94
     another
    0.93
     an
    0.90
     in
    0.88
    Activations Density 37.129%

    No Known Activations