© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    mentions of sports, particularly football

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act-logits · gemini-2.0-flash

    say "sports" Method used: 2 — because following tokens are NFL, NBA, Kings, hockey, etc. — say "sports"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    prefixer
    -0.67
    multer
    -0.65
     '\\;'
    -0.64
     InputDecoration
    -0.61
    StoryboardSegue
    -0.59
    yargs
    -0.59
    apimachinery
    -0.58
    UrlResolution
    -0.56
    OrWhiteSpace
    -0.55
    PMailer
    -0.54
    POSITIVE LOGITS
    box
    0.54
     preocupes
    0.54
     تانيه
    0.54
    FunctionFlags
    0.52
     pierdas
    0.50
    Nc
    0.49
     opérés
    0.49
    Box
    0.48
     distanciation
    0.47
     Men
    0.47
    Activations Density 4.541%

    No Known Activations