© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3770
    Prev
    Next
    INDEX
    Explanations

    the word "long" preceded by data types in code, and the words "longer" and "than."

    oai_token-act-pair · gemini-2.0-flash

    long

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     long
    -2.23
     longer
    -2.02
    long
    -2.02
     longest
    -2.00
     LONG
    -1.98
    LONG
    -1.87
    Long
    -1.86
     Long
    -1.81
    longer
    -1.77
    Longer
    -1.69
    POSITIVE LOGITS
    migrationBuilder
    0.81
    !*\
    0.77
    ViewFeatures
    0.71
     وتسجيلات
    0.69
    Дереккөздер
    0.67
     <<<<<<<<<<<<<<
    0.66
    IUrlHelper
    0.62
    MessageTagHelper
    0.60
     EconPapers
    0.60
    RenderAtEndOf
    0.60
    Activations Density 0.774%

    No Known Activations