© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4279
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly used in sports journalism, especially related to soccer/football

    oai_token-act-pair · gemini-2.0-flash

    Manchester United, soccer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     CSL
    -0.54
    比特派
    -0.53
     OSM
    -0.50
    featureID
    -0.48
     Fet
    -0.48
    FlowLayout
    -0.47
     ChatGPT
    -0.47
     Daf
    -0.47
    र्शन
    -0.47
     dago
    -0.47
    POSITIVE LOGITS
    thâu
    0.78
     defaultstate
    0.64
     unknownFields
    0.62
    RenderAtEndOf
    0.62
    SpringRunner
    0.60
     يتيمه
    0.60
    UrlResolution
    0.57
    Tē
    0.57
    yntaxException
    0.55
     ComVisible
    0.55
    Activations Density 0.795%

    No Known Activations