© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2147
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with quantitative scientific research

    oai_token-act-pair · gemini-2.0-flash

    quantitative/qualitative

    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
     thérape
    -0.59
     préférence
    -0.54
    TagMode
    -0.54
    !(:
    -0.52
    ệng
    -0.52
    IUCN
    -0.51
     genoux
    -0.51
    GraphicsUnit
    -0.51
     snippetHide
    -0.50
     кӀ
    -0.50
    POSITIVE LOGITS
    NameInMap
    0.56
    sizeCache
    0.54
    يكب
    0.54
    凭
    0.53
    ChildScrollView
    0.53
    ysan
    0.52
     odkazy
    0.51
     &___
    0.50
    sitive
    0.50
     فريبيس
    0.50
    Activations Density 2.240%

    No Known Activations