© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 356
    Prev
    Next
    INDEX
    Explanations

    words associated with history, regions, cultures, or people groups, especially in a context of governments or power

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Hauptartikel
    -0.54
    出版年
    -0.53
    izzati
    -0.52
    }))
    -0.52
    arbonato
    -0.51
    новништво
    -0.50
    pushFollow
    -0.49
     collectons
    -0.49
    はじめに
    -0.48
    гант
    -0.47
    POSITIVE LOGITS
     NUKAT
    0.60
     ujednoznacz
    0.59
     initComponents
    0.54
     disambiguazione
    0.53
     الرياضيه
    0.52
    Péri
    0.52
    hombo
    0.50
    PerformLayout
    0.50
     betweenstory
    0.50
    octanol
    0.49
    Activations Density 18.255%

    No Known Activations