© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9684
    Prev
    Next
    INDEX
    Explanations

    latex and code snippets interspersed in the text

    oai_token-act-pair · gemini-2.0-flash

    detects math and code

    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
     McNally
    -0.74
     Teb
    -0.67
     Barton
    -0.66
     Mee
    -0.63
    Rüyada
    -0.62
     Speedway
    -0.61
     Titus
    -0.59
     Mohamed
    -0.59
    Teb
    -0.58
     Scooby
    -0.58
    POSITIVE LOGITS
    ®
    0.58
     kertas
    0.58
     Tuttle
    0.55
    وائ
    0.52
     Ricardo
    0.52
    ％
    0.52
     compagni
    0.51
    (\
    0.51
    Ricardo
    0.51
     typelib
    0.50
    Activations Density 5.239%

    No Known Activations