© 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. 9717
    Prev
    Next
    INDEX
    Explanations

    discussions of email and software errors

    oai_token-act-pair · gemini-2.0-flash

    Computer errors and email

    np_max-act · 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
    mail
    -0.60
    <bos>
    -0.59
    quy
    -0.52
    riz
    -0.50
     closest
    -0.48
    ideae
    -0.48
     chuy
    -0.47
    oxidants
    -0.47
     hoá
    -0.47
    file
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.80
     snippetHide
    0.75
    Xna
    0.75
    AutoresizingMask
    0.70
    bootstrapcdn
    0.69
     initComponents
    0.68
    ValueStyle
    0.65
    epam
    0.65
    حوالہ
    0.62
     Italijanski
    0.62
    Activations Density 1.049%

    No Known Activations