© 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. 13934
    Prev
    Next
    INDEX
    Explanations

    words and phrases that represent points within a legal argument or discussion

    oai_token-act-pair · gemini-2.0-flash

    opinions and emphasis

    np_max-act · gemini-2.0-flash
    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
     useNavigate
    -0.57
    glBind
    -0.57
     useDispatch
    -0.57
    setArguments
    -0.56
    ContextCompat
    -0.56
    χρι
    -0.50
     locul
    -0.50
     déterminé
    -0.49
    WEBPACK
    -0.49
     useSelector
    -0.49
    POSITIVE LOGITS
    <bos>
    1.05
     cherchés
    0.92
     EconPapers
    0.84
    GEBURTSDATUM
    0.82
     Exacts
    0.78
    IntoConstraints
    0.77
     Paglinawan
    0.75
     ویکی‌پدی
    0.74
    RTEE
    0.70
     Signalez
    0.66
    Activations Density 3.405%

    No Known Activations