© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14308
    Prev
    Next
    INDEX
    Explanations

    mentions of the European Union alongside related words and pronouns.

    oai_token-act-pair · gemini-2.0-flash

    Union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.83
    '
    -0.66
    The
    -0.66
    A
    -0.62
    1
    -0.58
    2
    -0.57
    3
    -0.54
     the
    -0.52
     The
    -0.52
    ↵↵
    -0.51
    POSITIVE LOGITS
    MessageTagHelper
    0.83
     ErrIntOverflow
    0.81
     BrowserModule
    0.78
    +:+
    0.78
    SharedDtor
    0.77
     XCTest
    0.77
     שוליים
    0.76
    İstinadlar
    0.74
     متعلقه
    0.74
    pexpr
    0.73
    Activations Density 1.562%

    No Known Activations