© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8262
    Prev
    Next
    INDEX
    Explanations

    text including numerical percentages, currency, acronyms and quotations about money

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.68
    +#+#
    -0.60
    zele
    -0.56
    AnchorStyles
    -0.52
    雍
    -0.49
    ze
    -0.49
     Coss
    -0.47
    :-)
    -0.45
    GoogleApiClient
    -0.44
    penup
    -0.43
    POSITIVE LOGITS
    Демографія
    0.61
     TextAppearance
    0.54
    __).
    0.47
    latego
    0.47
    runOnUiThread
    0.44
    MessageOf
    0.43
     وتسجيلات
    0.42
    obiology
    0.41
     NgModule
    0.41
    AndEndTag
    0.41
    Activations Density 0.219%

    No Known Activations