© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15138
    Prev
    Next
    INDEX
    Explanations

    language from scientific or mathematical papers

    oai_token-act-pair · gemini-2.0-flash

    Theoretical physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Moulton
    -0.48
    __':
    -0.43
    hip
    -0.42
    join
    -0.41
     ihr
    -0.39
    petto
    -0.39
    APOLIS
    -0.38
    StringBuilder
    -0.37
     AssemblyCulture
    -0.36
    انجليز
    -0.36
    POSITIVE LOGITS
    StoryboardSegue
    0.83
    WebControls
    0.77
    findpost
    0.75
    AnchorStyles
    0.75
    AutoScaleMode
    0.68
     protoimpl
    0.67
    makeConstraints
    0.66
    CppMethod
    0.65
    enumi
    0.64
    LEADING
    0.64
    Activations Density 4.871%

    No Known Activations