© 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. 4444
    Prev
    Next
    INDEX
    Explanations

    references to legal documents such as patents and court papers

    oai_token-act-pair · gemini-2.0-flash

    U.S. Patents

    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
     Efq
    -1.19
     surla
    -1.07
    InjectAttribute
    -1.04
     itſelf
    -1.02
     ་་
    -1.02
     فريبيس
    -1.01
     myſelf
    -1.01
     Monfieur
    -1.00
     ―――――
    -1.00
     Италијани
    -0.99
    POSITIVE LOGITS
    {§
    0.23
    <eos>
    0.19
     l
    0.18
    2
    0.18
    [
    0.17
    {\$
    0.16
    {
    0.15
     I
    0.14
    {"
    0.14
      
    0.13
    Activations Density 0.292%

    No Known Activations