© 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
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 9436
    Prev
    Next
    INDEX
    Explanations

    text related to sports, especially baseball and soccer, with an emphasis on scores, players, and achievements

    oai_token-act-pair · gemini-2.0-flash

    Sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.52
     вжи
    -0.50
    γκ
    -0.43
    })();
    -0.40
    '){
    -0.40
    ログ
    -0.39
     signs
    -0.39
    chaft
    -0.39
    ostom
    -0.39
     calories
    -0.38
    POSITIVE LOGITS
    ValueGeneration
    1.02
    Geplaatst
    0.97
     pinulongan
    0.90
    ConstraintMaker
    0.87
    ########.
    0.81
    posedge
    0.79
    MLLoader
    0.79
     متعلقه
    0.79
    Autoritní
    0.78
     يتيمه
    0.75
    Activations Density 0.106%

    No Known Activations