© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 439
    Prev
    Next
    INDEX
    Explanations

    java, C#, and other programming language import statements, class names, and package names

    oai_token-act-pair · gemini-2.0-flash

    Map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -0.90
     فريبيس
    -0.85
     nakalista
    -0.79
    Portály
    -0.75
    ?");
    -0.74
    '):
    -0.74
    WebVitals
    -0.73
    ?";
    -0.72
    Rujuakan
    -0.71
     AssemblyCulture
    -0.69
    POSITIVE LOGITS
    DoubleQuotes
    0.52
    awaiter
    0.51
    aarrggbb
    0.44
    緒
    0.41
     protoimpl
    0.41
    ruptedException
    0.41
    اهش
    0.40
    msgSender
    0.40
    JpaRepository
    0.38
     dă
    0.38
    Activations Density 1.726%

    No Known Activations