© 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. 9298
    Prev
    Next
    INDEX
    Explanations

    technical language in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    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
     Carrasco
    -0.50
     FetchType
    -0.49
     ब्रेकडाउन
    -0.49
     scolaires
    -0.48
    WriteTagHelper
    -0.47
    océan
    -0.47
     Garantía
    -0.47
    Kedua
    -0.46
    randomUUID
    -0.46
     CHAPITRE
    -0.46
    POSITIVE LOGITS
     disambiguazione
    0.72
    RegressionTest
    0.64
     Tack
    0.58
    EnableWeb
    0.57
    OGND
    0.57
    ukone
    0.56
     NgModule
    0.56
    KommentareTeilen
    0.54
    PyExc
    0.54
     }}}
    0.53
    Activations Density 3.612%

    No Known Activations