© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10149
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically PHP code in one instance and journal article references in another

    oai_token-act-pair · gemini-2.0-flash

    code and technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     snippetHide
    -0.74
    ंदीखरीदारी
    -0.65
    ksikon
    -0.61
    المكان
    -0.56
     nakalista
    -0.55
    queryInterface
    -0.55
     '\\;'
    -0.54
    ParallelGroup
    -0.54
    MigrationBuilder
    -0.54
    GOTREF
    -0.52
    POSITIVE LOGITS
     refroidissement
    0.57
    richTextPanel
    0.53
     जहां
    0.52
     lenker
    0.51
     مُعرِّف
    0.49
    wem
    0.46
     труда
    0.45
    échal
    0.45
    Malawi
    0.44
    tető
    0.43
    Activations Density 1.311%

    No Known Activations