© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10504
    Prev
    Next
    INDEX
    Explanations

    text that is in french.

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fraî
    -0.52
     brillantes
    -0.52
     françaises
    -0.50
     natale
    -0.50
     quelconque
    -0.47
     russes
    -0.47
     nécessité
    -0.47
     familiari
    -0.46
     diversas
    -0.46
    ki
    -0.44
    POSITIVE LOGITS
    
    1.00
    ioutil
    0.88
     surla
    0.87
    WriteTagHelper
    0.86
    urlpatterns
    0.80
    sizeCache
    0.79
    mybatisplus
    0.79
    
    0.78
    afficheront
    0.78
    InjectAttribute
    0.77
    Activations Density 31.626%

    No Known Activations