© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6972
    Prev
    Next
    INDEX
    Explanations

    words related to business, specifically the names of companies, facilities, or concepts that are a part of a business

    oai_token-act-pair · gemini-2.0-flash

    Business, research reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoresizingMask
    -0.53
    mybatisplus
    -0.52
     utilisons
    -0.47
     ervan
    -0.45
    NullException
    -0.45
    AccessException
    -0.44
    fois
    -0.44
     aimez
    -0.43
     jadx
    -0.42
     traccia
    -0.42
    POSITIVE LOGITS
     estekak
    0.84
    sizeCache
    0.72
    Hentet
    0.66
    
    0.65
    }))
    0.65
    HtmlAttribute
    0.64
    Enllaces
    0.60
    englanniksi
    0.60
    UTIVE
    0.57
    queryInterface
    0.57
    Activations Density 26.670%

    No Known Activations