© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9631
    Prev
    Next
    INDEX
    Explanations

    the word "stock" when referring to the supply or inventory of some item

    oai_token-act-pair · gemini-2.0-flash

    stock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     stock
    -3.33
    stock
    -2.89
    Stock
    -2.88
     Stock
    -2.86
     STOCK
    -2.55
    STOCK
    -2.44
     stocks
    -2.14
    stocks
    -1.99
     Stocks
    -1.83
    Stocks
    -1.77
    POSITIVE LOGITS
    AndEndTag
    0.59
     AssemblyCompany
    0.58
     adaptées
    0.55
     devriez
    0.54
    espero
    0.54
     adaptés
    0.53
    djangoproject
    0.52
     devez
    0.52
    SPATH
    0.52
     aureus
    0.51
    Activations Density 0.643%

    No Known Activations