© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13335
    Prev
    Next
    INDEX
    Explanations

    words associated with monetary and business deals

    oai_token-act-pair · gemini-2.0-flash

    international companies/relations

    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
    +#+#
    -0.69
    AddTagHelper
    -0.66
    AntiForgeryToken
    -0.62
     ایشان
    -0.57
     beliau
    -0.56
    webElement
    -0.55
     presso
    -0.55
    がございます
    -0.54
     ·
    -0.53
     whilst
    -0.53
    POSITIVE LOGITS
     bosses
    0.66
     Hilfs
    0.65
    TagMode
    0.63
     Aids
    0.63
    出版年
    0.61
     intptr
    0.59
     ironing
    0.58
     quake
    0.58
    ukunft
    0.56
     booze
    0.56
    Activations Density 5.831%

    No Known Activations