© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1351
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and scientific language, but not consistently

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    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
     option
    -0.56
     defStyleAttr
    -0.54
    vement
    -0.53
     options
    -0.50
    Вариан
    -0.50
    mouseout
    -0.47
    option
    -0.46
     can
    -0.45
    LOAT
    -0.45
     variant
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.69
    awtextra
    0.65
    GEBURTSDATUM
    0.64
    PHeader
    0.63
     EconPapers
    0.63
    HtmlAttribute
    0.63
    ReusableCell
    0.62
    ImageContext
    0.61
     שוליים
    0.61
     sauvages
    0.61
    Activations Density 16.433%

    No Known Activations