© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9368
    Prev
    Next
    INDEX
    Explanations

    words and punctuation that come immediately before or after parenthesis

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act · gemini-2.0-flash

    ▁(

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
    ↵
    -1.27
    (
    -0.88
    '
    -0.82
    ↵↵↵
    -0.80
    ↵↵
    -0.80
     (
    -0.78
    <eos>
    -0.77
    D
    -0.75
     {
    -0.75
    S
    -0.70
    POSITIVE LOGITS
     Efq
    1.55
     Majefty
    1.52
     myſelf
    1.48
     itſelf
    1.45
     ſeveral
    1.44
     ſta
    1.44
     himſelf
    1.44
     Monfieur
    1.43
    neſs
    1.40
     ſtate
    1.39
    Activations Density 0.814%

    No Known Activations