© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 415
    Prev
    Next
    INDEX
    Explanations

    code-related things such as programming terms, copyright notices, and version numbers

    oai_token-act-pair · gemini-2.0-flash

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     transformation
    -0.90
     digital
    -0.90
    transformation
    -0.86
     Transformation
    -0.85
     transformations
    -0.79
     transition
    -0.79
     Digital
    -0.78
    digital
    -0.78
    DIGITAL
    -0.78
    Digital
    -0.77
    POSITIVE LOGITS
    __((
    0.60
    tagext
    0.60
    ="@+
    0.60
    MigrationBuilder
    0.57
    late
    0.56
    PMailer
    0.55
    CreateInfo
    0.55
     late
    0.53
    IsMutable
    0.53
     ويكيپيديا
    0.52
    Activations Density 0.253%

    No Known Activations