© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10857
    Prev
    Next
    INDEX
    Explanations

    french words in a technical conversation

    oai_token-act-pair · gemini-2.0-flash

    French

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.75
     sas
    -0.75
    SES
    -0.72
     SES
    -0.72
     Sas
    -0.71
     Sass
    -0.71
     Vos
    -0.71
     Gies
    -0.70
    ES
    -0.70
    es
    -0.70
    POSITIVE LOGITS
     OkHttpClient
    0.64
    Története
    0.61
    endwhile
    0.60
    coln
    0.59
    contentLoaded
    0.58
    antium
    0.57
     algodão
    0.57
    imantan
    0.57
     DataLoader
    0.57
     Donnelly
    0.56
    Activations Density 7.583%

    No Known Activations