© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4818
    Prev
    Next
    INDEX
    Explanations

    sentences talking negatively about a basketball player's defensive abilities

    oai_token-act-pair · gemini-2.0-flash

    basketball-related terms

    np_token-act-pair-logits · gpt-4o-mini

    basketball court

    np_max-act-logits · gemini-2.0-flash

    say "basketball"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     football
    -0.71
     Football
    -0.65
    football
    -0.62
    Football
    -0.61
     fútbol
    -0.60
     NFL
    -0.54
     fotbal
    -0.52
     fotball
    -0.51
     FOOTBALL
    -0.50
     futebol
    -0.49
    POSITIVE LOGITS
     court
    1.17
    court
    1.12
    basket
    1.04
     basket
    1.03
     baskets
    0.99
     Tip
    0.98
     Basket
    0.97
     Baskets
    0.96
    hoop
    0.93
     Hoop
    0.93
    Activations Density 0.665%

    No Known Activations