© 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. 325
    Prev
    Next
    INDEX
    Explanations

    words related to academic writing, research, and professional discussions

    oai_token-act-pair · gemini-2.0-flash

    scientific/formal writing

    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
    verwijspagina
    -0.82
     تضيفلها
    -0.81
     itſelf
    -0.77
    extAlignment
    -0.75
    _))
    -0.75
     themſelves
    -0.73
     Commencez
    -0.72
    XmlEnum
    -0.72
     ویکی‌پدیای
    -0.72
     perſon
    -0.71
    POSITIVE LOGITS
    terung
    0.41
    گردان
    0.38
     rotated
    0.38
    머
    0.37
     cioccolato
    0.37
    하
    0.36
     للاسماء
    0.35
     kering
    0.35
     genoemd
    0.35
    偏
    0.35
    Activations Density 35.004%

    No Known Activations