© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9708
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues or sports teams and their status

    oai_token-act-pair · gemini-2.0-flash

    football division

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    loem
    -0.61
     setAddress
    -0.60
     Waters
    -0.60
    واه
    -0.54
    istible
    -0.52
     Shadows
    -0.51
    figer
    -0.51
    GetBytes
    -0.50
    httphttps
    -0.50
    cookieParser
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.69
    脚注の使い方
    0.54
     חיצוניים
    0.54
     estimés
    0.52
    <%@
    0.49
    BeginContext
    0.48
    RotationOrder
    0.48
    DoubleQuotes
    0.47
    لينكات
    0.47
     riusc
    0.47
    Activations Density 1.041%

    No Known Activations