© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    sections of code related to assembly

    oai_token-act-pair · gemini-2.0-flash

    assembly

    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
    Personensuche
    -0.73
    Bibliograf
    -0.67
     autorytatywna
    -0.66
     célè
    -0.66
     feroit
    -0.63
     auroit
    -0.63
    Autoritní
    -0.61
     pouvoit
    -0.61
     rejoindre
    -0.60
    berdayakan
    -0.60
    POSITIVE LOGITS
    ]{
    0.71
     favor
    0.59
     astore
    0.51
     source
    0.51
    </b>
    0.50
    soka
    0.50
     '-':
    0.50
     Favor
    0.48
     *>
    0.48
    HasForeignKey
    0.47
    Activations Density 0.042%

    No Known Activations