© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 416
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences of hedging verbs in sentences with negative constraints

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -0.79
    <bos>
    -0.77
    adeloupe
    -0.70
    quiti
    -0.66
     ͜ʖ
    -0.66
    monton
    -0.66
    Hochspringen
    -0.66
     שוליים
    -0.66
    fowl
    -0.66
    neapolis
    -0.66
    POSITIVE LOGITS
    UnusedPrivate
    0.61
    exitRule
    0.48
    <eos>
    0.47
     zonne
    0.43
    DoubleQuotes
    0.41
     själva
    0.41
     følgende
    0.41
     piele
    0.40
     Obviously
    0.40
    --)
    0.39
    Activations Density 1.856%

    No Known Activations