© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2922
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to contracts, fraud, and warranties, often including company names

    oai_token-act-pair · gemini-2.0-flash

    Legal disputes involving Mercury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     vergeten
    -0.51
     kollek
    -0.47
     Company
    -0.44
     he
    -0.43
     verksamhet
    -0.42
    Fact
    -0.42
     group
    -0.39
     company
    -0.39
    führ
    -0.38
     him
    -0.38
    POSITIVE LOGITS
     propOrder
    1.18
    LookAnd
    0.96
     ddelweddau
    0.90
    InputTagHelper
    0.88
     الحره
    0.88
     للمعارف
    0.85
     ModelExpression
    0.84
    HtmlAttribute
    0.83
     @"/
    0.83
    EndInit
    0.82
    Activations Density 12.549%

    No Known Activations