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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10421
    Prev
    Next
    INDEX
    Explanations

    This neuron detects text about football (soccer) and marks the context depending on the club or people mentioned.

    oai_token-act-pair · gemini-2.0-flash

    Football management

    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
     kalın
    -0.46
     screen
    -0.45
    chluss
    -0.42
     kív
    -0.40
     desac
    -0.40
     ister
    -0.40
     divisa
    -0.40
     screening
    -0.39
    screen
    -0.39
     screens
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.98
    AnchorStyles
    0.83
    Personendaten
    0.82
     cherchés
    0.77
     الحره
    0.77
    Билгалдахарш
    0.72
    NameInMap
    0.71
    AxisAlignment
    0.69
    MENAFN
    0.69
     Infórmanos
    0.67
    Activations Density 0.825%

    No Known Activations