© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2432
    Prev
    Next
    INDEX
    Explanations

    words and phrases used when asking for or giving feedback or instructions

    oai_token-act-pair · gemini-2.0-flash

    comments or questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AddTagHelper
    -0.72
    ulemon
    -0.61
    AndEndTag
    -0.61
    utnik
    -0.57
    Izvori
    -0.56
     traditionnels
    -0.56
     @"/
    -0.56
    ViewImports
    -0.56
    clerview
    -0.54
    agaimana
    -0.54
    POSITIVE LOGITS
    saraba
    0.56
    Rohy
    0.55
    CrossRef
    0.52
     متعلقه
    0.50
    出版年
    0.50
    Населення
    0.49
    InstrumentedTest
    0.48
     Screens
    0.48
     screens
    0.48
    screens
    0.47
    Activations Density 0.905%

    No Known Activations