© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12572
    Prev
    Next
    INDEX
    Explanations

    the names of politicians, twitter and IRC logs

    oai_token-act-pair · gemini-2.0-flash

    political commentary and discussion

    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
     étrangères
    -0.48
    foreign
    -0.41
    P
    -0.41
    cusión
    -0.41
    instancetype
    -0.41
    istan
    -0.41
    ruecos
    -0.40
    G
    -0.40
     infância
    -0.39
     foreign
    -0.38
    POSITIVE LOGITS
     ModelExpression
    0.98
    出版年
    0.87
     StatefulWidget
    0.79
    Hentet
    0.76
     defaultstate
    0.75
     gyhoeddwyd
    0.75
     <<<<<<<<<<<<<<
    0.74
    transQ
    0.73
    webElementXpaths
    0.73
    RegressionTest
    0.68
    Activations Density 1.395%

    No Known Activations