© 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. 9966
    Prev
    Next
    INDEX
    Explanations

    the names of soccer leagues and teams

    oai_token-act-pair · gemini-2.0-flash

    League

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.56
     descon
    -0.48
    ọn
    -0.45
    -
    -0.42
    Con
    -0.42
    Der
    -0.42
      
    -0.41
    The
    -0.41
     somewhere
    -0.41
     con
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.88
    曖昧さ回避
    0.84
    WebElementEntity
    0.82
    :✨
    0.78
     &___
    0.76
    XmlAccessorType
    0.75
    berdayakan
    0.75
    Viitteet
    0.75
    MessageTagHelper
    0.73
    yntaxException
    0.73
    Activations Density 0.386%

    No Known Activations