© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3846
    Prev
    Next
    INDEX
    Explanations

    words related to historical facts, inventions, and processes

    oai_token-act-pair · gemini-2.0-flash

    found

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    existent
    -0.63
    发现
    -0.58
     trouvez
    -0.57
    finding
    -0.57
    FIND
    -0.57
     FINDINGS
    -0.56
     finding
    -0.56
     finds
    -0.56
     eût
    -0.56
    發現
    -0.55
    POSITIVE LOGITS
     يتيمه
    0.72
    <bos>
    0.60
    RegressionTest
    0.59
     незавершена
    0.58
    EDEFAULT
    0.57
     in
    0.52
    脚注の使い方
    0.51
    
    0.50
    ThroughAttribute
    0.49
    MathML
    0.49
    Activations Density 12.022%

    No Known Activations