© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12567
    Prev
    Next
    INDEX
    Explanations

    java code snippets, specifically relating to conditional statements and XML parsing

    oai_token-act-pair · gemini-2.0-flash

    equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.74
    equals
    -0.54
     getItemId
    -0.48
    Demonstration
    -0.44
    illos
    -0.44
     initComponents
    -0.43
    InstrumentedTest
    -0.42
    ことなく
    -0.41
     stä
    -0.41
    の前に
    -0.40
    POSITIVE LOGITS
    PerformLayout
    0.77
     Roskov
    0.71
    InjectAttribute
    0.69
    itespace
    0.66
     оригіналу
    0.64
     pleaſure
    0.64
     تضيفلها
    0.62
    CodeDom
    0.60
    AntiForgeryToken
    0.60
    FTFY
    0.59
    Activations Density 4.478%

    No Known Activations