© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6011
    Prev
    Next
    INDEX
    Explanations

    technical or research documents, possibly figures or experimental results

    oai_token-act-pair · gemini-2.0-flash

    figure captions and labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.76
    '
    -0.63
    .
    -0.61
     
    -0.56
    <strong>
    -0.56
    ’
    -0.55
    <b>
    -0.49
    ↵↵
    -0.49
    ↵
    -0.46
    <h2>
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.86
    SequentialGroup
    0.80
    makeConstraints
    0.79
    WebVitals
    0.75
     nakalista
    0.71
     EconPapers
    0.71
     שוליים
    0.68
     propOrder
    0.68
     chré
    0.66
    rawDesc
    0.66
    Activations Density 3.870%

    No Known Activations