© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    code snippets, file names, and structured data with patterns involving periods and specific keywords like "data", "name", "NGX", "uri", and "Effect".

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     CreateTagHelper
    -0.99
     createState
    -0.81
     للمعارف
    -0.78
     Efq
    -0.72
     Reſ
    -0.72
    MigrationBuilder
    -0.71
    WindowConstants
    -0.71
    <bos>
    -0.68
    contentLoaded
    -0.67
    MLLoader
    -0.66
    POSITIVE LOGITS
    ()]
    0.52
    b
    0.47
    vent
    0.46
    derive
    0.44
    冕
    0.44
    kheim
    0.44
    ​​
    0.43
    ppen
    0.43
    simov
    0.43
    }`}
    0.42
    Activations Density 3.679%

    No Known Activations