© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7220
    Prev
    Next
    INDEX
    Explanations

    references to determining an order or sequence of steps

    oai_token-act-pair · gemini-2.0-flash

    words related to order and structure

    np_token-act-pair-logits · gpt-4o-mini

    order

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     order
    -1.57
     Order
    -1.53
    order
    -1.47
    Order
    -1.44
     ORDER
    -1.41
     Orders
    -1.33
    ORDER
    -1.27
     ordering
    -1.25
     Ordering
    -1.23
     orders
    -1.21
    POSITIVE LOGITS
    TagMode
    0.67
    der
    0.62
     المعيارى
    0.60
    SourceChecksum
    0.59
    ders
    0.59
     Pingback
    0.55
     AssemblyTitle
    0.51
    acquisto
    0.50
     AllMovie
    0.49
     متعلقه
    0.48
    Activations Density 1.877%

    No Known Activations