© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9691
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the stock market and economic news

    oai_token-act-pair · gemini-2.0-flash

    Jones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -0.59
    "){
    -0.57
     agon
    -0.53
     StatefulWidget
    -0.52
     MainAxisSize
    -0.48
    日閲覧
    -0.46
    ?".
    -0.46
    ?")
    -0.46
    ?’
    -0.44
    __':
    -0.44
    POSITIVE LOGITS
    httphttps
    0.64
    +#+
    0.63
    CloseOperation
    0.61
     LCCN
    0.60
    MessageOf
    0.60
     <>",
    0.60
     Roskov
    0.59
    abstractmethod
    0.59
    })));
    0.57
     виправивши
    0.57
    Activations Density 1.739%

    No Known Activations