© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13567
    Prev
    Next
    INDEX
    Explanations

    Japanese names, places, organizations and media related to sports or entertainment

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reflexes
    -0.49
     Virtually
    -0.48
     épic
    -0.45
    alium
    -0.45
    новниш
    -0.44
    募
    -0.44
    もしれない
    -0.43
    UELA
    -0.43
     vektör
    -0.43
    acy
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.99
    makeConstraints
    0.76
    protoimpl
    0.75
     незавершена
    0.75
    脚注の使い方
    0.72
    tvguidetime
    0.69
    onAttach
    0.68
    RectangleBorder
    0.67
    ViewImports
    0.66
    WaitGroup
    0.65
    Activations Density 2.899%

    No Known Activations