© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13439
    Prev
    Next
    INDEX
    Explanations

    terms related to business functions, such as finance, sales, or shipping.

    oai_token-act-pair · gemini-2.0-flash

    business/commerce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.86
    ंदीखरीदारी
    -0.76
    Portale
    -0.70
     مشين
    -0.67
     Retail
    -0.66
    новништво
    -0.66
    Datuak
    -0.64
    VersionUID
    -0.63
     retail
    -0.63
     مرئيه
    -0.62
    POSITIVE LOGITS
    TagMode
    0.58
    lgari
    0.50
    ymce
    0.47
    ISupport
    0.46
     "="
    0.45
    ništvo
    0.44
     seguido
    0.43
    setti
    0.43
    ędzy
    0.43
    ellschaft
    0.42
    Activations Density 2.625%

    No Known Activations