© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3815
    Prev
    Next
    INDEX
    Explanations

    words that look like scientific codes or words from languages other than English

    oai_token-act-pair · gemini-2.0-flash

    Virus research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    SpringBootTest
    -0.85
    afficheront
    -0.79
    存于互联网档案馆
    -0.74
    verwijspagina
    -0.71
    GEBURTSDATUM
    -0.66
     Preferencias
    -0.66
    featureID
    -0.65
    UrlResolution
    -0.63
     typelib
    -0.61
     fú
    -0.61
    POSITIVE LOGITS
    heil
    0.48
    ".
    0.48
    atillo
    0.47
    zzleHttp
    0.46
    ..."
    0.46
    isRequired
    0.45
    rasil
    0.45
     توانند
    0.45
    ereza
    0.45
    hasia
    0.45
    Activations Density 1.088%

    No Known Activations