© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4289
    Prev
    Next
    INDEX
    Explanations

    symbols used in math and logic equations, including parentheses, letters used as variable names, and numerical operators.

    oai_token-act-pair · gemini-2.0-flash

    Math questions with choices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     B
    -2.22
     b
    -2.16
    B
    -1.85
    b
    -1.59
     getB
    -1.37
    getB
    -1.30
     б
    -1.27
    B
    -1.23
     Б
    -1.11
     ب
    -1.09
    POSITIVE LOGITS
    +#+
    0.73
    ✨:
    0.66
    sunt
    0.56
    RetentionPolicy
    0.55
    PerformLayout
    0.54
     uintptr
    0.52
    ainville
    0.52
    zielle
    0.51
    fromnode
    0.50
    atán
    0.50
    Activations Density 2.706%

    No Known Activations