© 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. 2820
    Prev
    Next
    INDEX
    Explanations

    single and multi digit numbers, and letters attached to numbers.

    oai_token-act-pair · gemini-2.0-flash

    numbers and codes

    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
     ModelExpression
    -0.81
     فريبيس
    -0.77
    +#+
    -0.69
    enterOuterAlt
    -0.65
     TextInputType
    -0.59
    >{@
    -0.57
    webElementGuid
    -0.55
    ViewFeatures
    -0.55
    المناصب
    -0.54
     AssemblyCompany
    -0.54
    POSITIVE LOGITS
    NAMESPACE
    0.50
    lemény
    0.46
     مواليد
    0.45
    USF
    0.45
     vry
    0.44
     Cassandra
    0.43
    URB
    0.43
    QJ
    0.43
    ilha
    0.43
    isser
    0.43
    Activations Density 5.263%

    No Known Activations