© 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. 479
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and their findings

    oai_token-act-pair · gemini-2.0-flash

    results

    np_max-act · 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
     Results
    -1.13
     results
    -1.08
    Result
    -1.06
     Result
    -1.06
     RESULTS
    -1.05
    Results
    -1.03
     result
    -0.99
     résultats
    -0.99
     resultados
    -0.99
     risultato
    -0.96
    POSITIVE LOGITS
     للمعارف
    0.74
    WithIOException
    0.59
     препратки
    0.55
    :✨
    0.53
     Trento
    0.51
    (;;)
    0.50
    tamment
    0.49
     TableColumn
    0.47
     Maggiore
    0.47
    _));
    0.47
    Activations Density 24.112%

    No Known Activations