© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10925
    Prev
    Next
    INDEX
    Explanations

    numbers, units of measure, and some associated descriptive words, especially in a food or technical context.

    oai_token-act-pair · gemini-2.0-flash

    weights and measures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     متعلقه
    -0.98
     المعيارى
    -0.97
    InputBorder
    -0.90
    SharedCtor
    -0.87
    Autoritní
    -0.86
    rungsseite
    -0.84
    EndContext
    -0.83
     ComVisible
    -0.80
    +#+#
    -0.77
    ConstraintMaker
    -0.77
    POSITIVE LOGITS
    g
    0.56
    cor
    0.53
     tri
    0.51
    XmlType
    0.50
    def
    0.48
    cl
    0.48
     cor
    0.47
    dine
    0.45
    fa
    0.44
    G
    0.44
    Activations Density 3.272%

    No Known Activations