© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11525
    Prev
    Next
    INDEX
    Explanations

    a combination of mathematical formulas and specific words such as "who," "has," and "there."

    oai_token-act-pair · gemini-2.0-flash

    JavaScript or programming syntax elements

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

    formula

    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
    ьаж
    -0.83
    XmlAccessType
    -0.79
     متعلقه
    -0.79
     utafitiHapana
    -0.75
     association
    -0.72
    UserScript
    -0.70
    хьтан
    -0.69
    IntoConstraints
    -0.69
     EconPapers
    -0.68
    ⓧ
    -0.67
    POSITIVE LOGITS
     rastre
    0.43
    ")){
    0.41
     Sta
    0.41
    )":
    0.41
    racuse
    0.39
     vast
    0.39
    toThrow
    0.39
     unlikely
    0.39
    awaiter
    0.38
    "){
    0.37
    Activations Density 0.180%

    No Known Activations