© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13571
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams, players, and positions

    oai_token-act-pair · gemini-2.0-flash

    sports/football

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <tbody>
    -0.46
    <eos>
    -0.45
     Mon
    -0.43
     rowspan
    -0.42
     .
    -0.41
    Mon
    -0.41
     
    -0.41
    态
    -0.40
     push
    -0.39
    }{{\
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.99
     समीक्षाओं
    0.89
     pleaſure
    0.86
    XmlAccessType
    0.80
     Monfieur
    0.77
     ―――――
    0.77
     resourceCulture
    0.76
     <=",
    0.75
    SizeMode
    0.75
    typeorm
    0.75
    Activations Density 1.387%

    No Known Activations