© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12991
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms related to outcomes and results

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     незавершена
    -0.72
     مرئيه
    -0.67
    RegressionTest
    -0.62
     समीक्षक
    -0.61
     ModelExpression
    -0.61
     ligiloj
    -0.60
    FXMLLoader
    -0.59
     Superhost
    -0.59
     correctes
    -0.59
    ItemBackground
    -0.58
    POSITIVE LOGITS
    음
    0.42
    AxisAlignment
    0.42
     interaction
    0.39
    OrFail
    0.38
    tamia
    0.38
    hamcrest
    0.38
    QApplication
    0.38
    exc
    0.38
    Eastern
    0.37
     counts
    0.37
    Activations Density 0.625%

    No Known Activations