© 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. 9400
    Prev
    Next
    INDEX
    Explanations

    words ending in "le" and some other seemingly random rare words

    oai_token-act-pair · 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
     autorytatywna
    -1.05
     الحره
    -1.04
     ویکی‌پدی
    -0.90
    Personendaten
    -0.87
     kaarangay
    -0.83
    oa̍t
    -0.83
     Réponses
    -0.78
     numberOfRows
    -0.77
     Numerade
    -0.75
    celotti
    -0.75
    POSITIVE LOGITS
     federal
    0.38
     Federal
    0.37
     nasional
    0.36
    Preced
    0.34
    锦
    0.34
     vlast
    0.34
    display
    0.34
    Imp
    0.33
    Which
    0.33
     çı
    0.33
    Activations Density 3.809%

    No Known Activations