© 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. 10626
    Prev
    Next
    INDEX
    Explanations

    text about India and politics, specifically elections, locations and violence, suggesting it may be related to news articles

    oai_token-act-pair · gemini-2.0-flash

    place names

    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
    :✨
    -0.71
    adaptiveStyles
    -0.68
    blurRadius
    -0.54
    ardless
    -0.54
     confronti
    -0.52
    WithIOException
    -0.52
    Big
    -0.52
     JpaRepository
    -0.51
     RoutedEventArgs
    -0.50
    RemoveField
    -0.49
    POSITIVE LOGITS
    ########.
    0.74
     calendriers
    0.71
     ***!
    0.60
     Autorizaciones
    0.56
     <",
    0.55
    heimer
    0.54
     beginnetje
    0.54
    Geschiedenis
    0.52
     Савезне
    0.50
    SharedDtor
    0.49
    Activations Density 0.698%

    No Known Activations