© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5104
    Prev
    Next
    INDEX
    Explanations

    words or labels in scientific papers related to graphs, lines, data and analysis

    oai_token-act-pair · gemini-2.0-flash

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    prefixer
    -0.70
    ]")]
    -0.68
    QMetaType
    -0.65
    IsContent
    -0.60
    endwhile
    -0.59
     createContext
    -0.59
    GEBURTSDATUM
    -0.59
     GreatSchools
    -0.57
    __':
    -0.57
    </thead>
    -0.57
    POSITIVE LOGITS
    CPtr
    0.56
    protoimpl
    0.52
     kalangan
    0.48
     llaman
    0.48
    pan
    0.48
     viață
    0.47
     căr
    0.47
    <bos>
    0.47
     pan
    0.46
    Links
    0.45
    Activations Density 7.766%

    No Known Activations