© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3102
    Prev
    Next
    INDEX
    Explanations

    the word "source"

    oai_token-act-pair · gemini-2.0-flash

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     source
    -1.23
    source
    -0.97
     sources
    -0.92
     Source
    -0.81
    Source
    -0.77
     in
    -0.62
     fuente
    -0.55
     to
    -0.55
    ource
    -0.54
     SOURCE
    -0.50
    POSITIVE LOGITS
    __*/
    1.14
    ThroughAttribute
    1.10
     tartalomajánló
    1.09
    interopRequire
    1.05
    webElementXpaths
    1.04
    MessageOf
    1.01
    complexContent
    1.00
    MigrationBuilder
    0.96
     disambiguazione
    0.93
    ViewImports
    0.93
    Activations Density 2.241%

    No Known Activations