© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10216
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by "a" or something said by someone.

    oai_token-act-pair · gemini-2.0-flash

    Articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Попис
    -0.89
     snippetHide
    -0.81
    antMatchers
    -0.78
    ThroughAttribute
    -0.77
    ArrowToggle
    -0.75
     Italijanski
    -0.74
    Хьажоргаш
    -0.74
    featureID
    -0.73
     ModelExpression
    -0.73
     disambiguazione
    -0.72
    POSITIVE LOGITS
     a
    1.90
     an
    1.44
     sebuah
    1.01
     einer
    0.97
     isang
    0.94
     یک
    0.92
    一个
    0.90
     eine
    0.90
     seorang
    0.89
     một
    0.86
    Activations Density 1.877%

    No Known Activations