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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8376
    Prev
    Next
    INDEX
    Explanations

    text related to sheets of material or comparing items

    oai_token-act-pair · gemini-2.0-flash

    sheet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     resourceCulture
    -1.66
     CreateTagHelper
    -1.64
    IntoConstraints
    -1.59
     <=",
    -1.51
    Tembelea
    -1.50
    تقاوى
    -1.49
    Personensuche
    -1.44
    :✨
    -1.41
     defaultstate
    -1.41
    ValueStyle
    -1.39
    POSITIVE LOGITS
     in
    0.90
    ’
    0.79
    '
    0.76
    o
    0.74
    e
    0.73
    -
    0.73
    /
    0.72
    i
    0.71
     we
    0.71
    en
    0.71
    Activations Density 1.619%

    No Known Activations