© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    words and characters from foreign languages, code, and other non-English text

    oai_token-act-pair · gemini-2.0-flash

    gi

    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
     nationaux
    -0.60
     vícti
    -0.57
     bibliothèque
    -0.56
     vocale
    -0.56
     individuelles
    -0.52
    doch
    -0.51
     Irrigation
    -0.49
     boto
    -0.48
     gand
    -0.48
    ัติ
    -0.47
    POSITIVE LOGITS
    writeField
    0.64
     CURIAM
    0.64
    CloseOperation
    0.64
     autorytatywna
    0.62
    TagMode
    0.59
    دانشنامهٔ
    0.59
     Taktlose
    0.59
    WSGI
    0.57
    czej
    0.55
     @"/
    0.54
    Activations Density 9.521%

    No Known Activations