© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5091
    Prev
    Next
    INDEX
    Explanations

    words and phrases that frequently follow the word "the" (e.g., "the country," "the nation")

    oai_token-act-pair · gemini-2.0-flash

    possession

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     adopted
    -0.50
     penyer
    -0.50
     incorpora
    -0.49
    adopted
    -0.49
    Adopted
    -0.48
    incorpor
    -0.47
    ियाँ
    -0.45
     adopt
    -0.45
     abbraccio
    -0.44
    rektur
    -0.43
    POSITIVE LOGITS
     protoimpl
    0.86
     nakalista
    0.83
     nonUne
    0.82
     Wicidata
    0.81
    matchCondition
    0.79
    aarrggbb
    0.79
    makeConstraints
    0.79
     autorytatywna
    0.78
    Šaltiniai
    0.77
    MigrationBuilder
    0.77
    Activations Density 38.549%

    No Known Activations