© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    text about the Arizona Cardinals and Philadelphia Eagles during football season

    oai_token-act-pair · gemini-2.0-flash

    Sports team performance

    np_max-act-logits · gemini-2.0-flash
    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
    fuls
    -0.62
    最快更新
    -0.62
    rotum
    -0.60
     harem
    -0.60
    ="@+
    -0.60
     Futuro
    -0.57
     Tante
    -0.55
     pavements
    -0.54
    aneous
    -0.54
     thither
    -0.53
    POSITIVE LOGITS
     coming
    0.96
     COMING
    0.70
     Coming
    0.68
    coming
    0.67
    Coming
    0.61
    OGND
    0.60
    contentLoaded
    0.56
    EDEFAULT
    0.52
    dert
    0.52
    protoc
    0.50
    Activations Density 1.661%

    No Known Activations