© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15322
    Prev
    Next
    INDEX
    Explanations

    French words and abbreviations, especially in the context of computer-related chat.

    oai_token-act-pair · gemini-2.0-flash

    foreign language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    queryInterface
    -0.82
    Sucesor
    -0.75
     Audiodateien
    -0.66
    SequentialGroup
    -0.61
     estimés
    -0.60
     doInBackground
    -0.57
    Personensuche
    -0.56
    Mga
    -0.56
    principalTable
    -0.54
    Tracce
    -0.54
    POSITIVE LOGITS
     a
    0.90
     Exactos
    0.59
     EN
    0.54
     En
    0.52
     а
    0.51
    En
    0.51
    EN
    0.50
    ++]=
    0.50
     A
    0.50
    a
    0.48
    Activations Density 1.865%

    No Known Activations