© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12445
    Prev
    Next
    INDEX
    Explanations

    parts of the code that describe the parameters of a product, such as "barcode", "Price" and "Cash Back"

    oai_token-act-pair · gemini-2.0-flash

    Data entries with prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -1.22
     Мексичка
    -0.64
    rungsseite
    -0.64
    PreferredItem
    -0.62
    libft
    -0.61
    ukone
    -0.60
    GEBURTSDATUM
    -0.59
    WebElementEntity
    -0.56
    ttemberg
    -0.55
     betale
    -0.54
    POSITIVE LOGITS
    expandindo
    0.59
     contextLoads
    0.58
     CreateTagHelper
    0.57
     BorderSide
    0.57
    bkz
    0.52
     broadcasters
    0.51
     ASPECTS
    0.50
    gemeinden
    0.50
     anyone
    0.50
     PROCEDURES
    0.50
    Activations Density 3.403%

    No Known Activations