© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4574
    Prev
    Next
    INDEX
    Explanations

    font awesome classes for plus/minus icons

    oai_token-act-pair · gemini-2.0-flash

    fa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fa
    -1.53
    fa
    -1.25
    Fa
    -1.17
     Fa
    -1.08
    <bos>
    -0.83
    FA
    -0.68
     FA
    -0.61
    giphy
    -0.59
    fas
    -0.58
    faa
    -0.56
    POSITIVE LOGITS
     StatelessWidget
    0.82
    
    0.77
     EconPapers
    0.77
     SafeMath
    0.73
    eterangan
    0.72
     makeStyles
    0.70
     fieldNum
    0.69
    #+#
    0.68
     Wikimédia
    0.67
    ividual
    0.66
    Activations Density 0.393%

    No Known Activations