© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    math and programming related terms, like numbers, logic operators, and arrays

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · 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
    AsUp
    -0.56
     kokona
    -0.51
     onOptions
    -0.51
     üzere
    -0.50
    ècie
    -0.50
    erals
    -0.49
    rawDesc
    -0.47
    MLLoader
    -0.46
    writerow
    -0.46
    listdir
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.77
     विश्वसनीयता
    0.58
    ollectionView
    0.56
    <table>
    0.52
    ługi
    0.50
    
    0.49
    Lähteet
    0.49
     pageContext
    0.49
    |}{}
    0.49
     involved
    0.49
    Activations Density 1.616%

    No Known Activations