© 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. 14007
    Prev
    Next
    INDEX
    Explanations

    scientific and technical language, particularly terms and abbreviations common in medical and materials science texts.

    oai_token-act-pair · gemini-2.0-flash

    hy

    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
     myſelf
    -1.12
     purpoſe
    -0.99
     itſelf
    -0.93
     themſelves
    -0.92
     faſt
    -0.92
     pleaſure
    -0.92
     himſelf
    -0.90
     leaſt
    -0.90
     Houſe
    -0.88
    ſelf
    -0.87
    POSITIVE LOGITS
    Geplaatst
    0.57
    ↵
    0.56
     met
    0.50
     der
    0.45
    <eos>
    0.45
    исленность
    0.45
     
    0.44
     G
    0.43
    .,
    0.43
    migrationBuilder
    0.43
    Activations Density 7.883%

    No Known Activations