© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9213
    Prev
    Next
    INDEX
    Explanations

    words that could be used in academic papers, including equation symbols, labels like "Fig", references, and section headings

    oai_token-act-pair · gemini-2.0-flash

    Introductory phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ])));
    -0.66
     [],
    -0.60
    `,
    -0.59
     deines
    -0.57
    ControllerTest
    -0.54
     iprot
    -0.53
     Савезне
    -0.53
    }\]
    -0.52
    /');
    -0.52
    êtement
    -0.51
    POSITIVE LOGITS
    出版年
    0.60
    StoryboardSegue
    0.59
    Referencie
    0.57
     GreatSchools
    0.55
     egiten
    0.54
     pestañas
    0.52
    Weblinks
    0.52
     Normdatei
    0.51
     Cataloging
    0.50
    UnitTesting
    0.49
    Activations Density 14.435%

    No Known Activations