© 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. 11709
    Prev
    Next
    INDEX
    Explanations

    words associated with mathematics and science

    oai_token-act-pair · gemini-2.0-flash

    non-English terms and symbols

    np_token-act-pair-logits · gpt-4o-mini
    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
    yield
    -0.48
     lie
    -0.47
     yield
    -0.45
     Yield
    -0.45
    parsedMessage
    -0.44
    >>
    -0.44
    Yield
    -0.42
     liggen
    -0.42
    adé
    -0.41
    例句
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.74
    المناصب
    0.72
    Personendaten
    0.71
    InjectAttribute
    0.69
    DoubleQuotes
    0.68
    تقاوى
    0.68
     itſelf
    0.66
    ArrowToggle
    0.65
    OGND
    0.65
    الحياه
    0.63
    Activations Density 2.689%

    No Known Activations