© 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. 13839
    Prev
    Next
    INDEX
    Explanations

    mentions of "CD" followed by a number, which likely represents a protein or marker

    oai_token-act-pair · gemini-2.0-flash

    CD

    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
     CD
    -0.79
    CD
    -0.69
    CDs
    -0.56
    MigrationBuilder
    -0.55
     fides
    -0.52
     cd
    -0.52
    cd
    -0.51
    eclampsia
    -0.48
    pc
    -0.48
     CDs
    -0.48
    POSITIVE LOGITS
     ostavi
    0.78
    Демографія
    0.74
     Houſe
    0.72
     Савезне
    0.69
     houſe
    0.68
     Diſ
    0.68
     Reſ
    0.67
     Anſ
    0.66
     itſelf
    0.65
     Perſ
    0.65
    Activations Density 1.130%

    No Known Activations