© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2896
    Prev
    Next
    INDEX
    Explanations

    french words and phrases

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act-logits · gemini-2.0-flash

    French

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ⓧ
    -0.93
     CascadeType
    -0.66
    contentLoaded
    -0.65
    nodoc
    -0.65
     TextInputType
    -0.63
    tabol
    -0.63
     Wikispecies
    -0.62
     CommonModule
    -0.60
     مرئيه
    -0.60
    simpleType
    -0.60
    POSITIVE LOGITS
    PMailer
    0.49
    出版年
    0.48
    findpost
    0.45
    AutoField
    0.43
    wną
    0.43
    orino
    0.43
     جمهور
    0.43
    ИА
    0.42
     än
    0.40
    Personendaten
    0.40
    Activations Density 0.803%

    No Known Activations