© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3564
    Prev
    Next
    INDEX
    Explanations

    words pertaining to the legal system, intentions, and numbers

    oai_token-act-pair · gemini-2.0-flash

    requirements

    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
    chromedriver
    -0.52
    Inject
    -0.49
    llingen
    -0.48
    킨
    -0.46
     iArr
    -0.46
    endent
    -0.46
    脚注の使い方
    -0.45
     Keeps
    -0.44
    BYE
    -0.44
     Tr
    -0.44
    POSITIVE LOGITS
    HtmlAttribute
    0.94
    ToAction
    0.69
    تقاوى
    0.68
    Geplaatst
    0.65
    المناصب
    0.65
    ViewFeatures
    0.63
    الإنجليزية
    0.62
    ImageContext
    0.62
    AndEndTag
    0.61
    Бахар
    0.60
    Activations Density 2.616%

    No Known Activations