© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    that appear to be related to professional sports teams, technical specifications, legal citations, and manufacturing assembly plants

    oai_token-act-pair · gemini-2.0-flash

    Numerical data/statistics

    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
    Negative Logits
    enumi
    -0.47
    BeforeMethod
    -0.46
     again
    -0.45
    Vidi
    -0.44
    AMER
    -0.43
     ويكيپيديا
    -0.39
    []{"
    -0.38
     sử
    -0.38
    arResult
    -0.38
    []{
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.79
     nakalista
    0.78
    URLException
    0.73
     EconPapers
    0.71
    multer
    0.68
    VersionUID
    0.64
    featureID
    0.60
    AddTagHelper
    0.59
     AudioClip
    0.58
    dating
    0.57
    Activations Density 14.117%

    No Known Activations