© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    journalistic writing, especially newspapers, including references to journalists, newspapers and reporting

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
     MainAxisSize
    -0.90
     EconPapers
    -0.88
    setVerticalGroup
    -0.76
    DockStyle
    -0.76
     purpoſe
    -0.73
     ſche
    -0.69
     '\\;'
    -0.68
     BorderRadius
    -0.68
     TextAlign
    -0.66
     Jefus
    -0.66
    POSITIVE LOGITS
    itinéraire
    0.48
     ihop
    0.42
    Autoritní
    0.41
    rmızı
    0.41
    Geographie
    0.40
     deaktiviert
    0.40
     i
    0.40
     Bon
    0.38
    Bon
    0.38
     White
    0.36
    Activations Density 1.158%

    No Known Activations