© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    instances of something being more than something else

    oai_token-act-pair · gemini-2.0-flash

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    protoimpl
    -0.91
     оригіналу
    -0.71
    TestingModule
    -0.71
    webElementXpaths
    -0.65
    LookAnd
    -0.63
     ostavi
    -0.58
    CodeAttribute
    -0.57
    Перед
    -0.57
    Chham
    -0.57
    Personensuche
    -0.57
    POSITIVE LOGITS
    ulite
    0.53
    ípio
    0.52
     Vole
    0.49
    Webpack
    0.49
     nämlich
    0.49
    InfoWindow
    0.49
    iecie
    0.49
    delion
    0.48
     ajan
    0.48
    avares
    0.48
    Activations Density 1.547%

    No Known Activations