© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9848
    Prev
    Next
    INDEX
    Explanations

    parts of 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_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
    Negative Logits
    SharedDtor
    -0.71
     gynhyrchwyd
    -0.66
    stylers
    -0.60
     للمعارف
    -0.60
    djangoproject
    -0.57
     okuyayım
    -0.57
     تضيفلها
    -0.57
     Normdatei
    -0.57
     препратки
    -0.56
    devise
    -0.55
    POSITIVE LOGITS
    ContentAsync
    0.54
     himself
    0.53
     onAnimation
    0.53
    pova
    0.53
    }{*}{
    0.52
    ništ
    0.52
    verage
    0.50
     Isidro
    0.49
    лок
    0.49
    []{"
    0.48
    Activations Density 0.897%

    No Known Activations