© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11650
    Prev
    Next
    INDEX
    Explanations

    language related to feature selection algorithms, especially in the context of distributed computing and scalability

    oai_token-act-pair · gemini-2.0-flash

    Data analysis algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     بتاريخ
    -0.52
     Hoboken
    -0.50
    elerik
    -0.48
    بوابة
    -0.47
     inoxydable
    -0.46
     Weldon
    -0.46
     Lakeland
    -0.46
    
    -0.45
     gloria
    -0.44
    qrstuvwxyz
    -0.43
    POSITIVE LOGITS
     estimés
    0.61
    TextWatcher
    0.60
     voren
    0.59
     estekak
    0.59
    Enllaces
    0.54
     intptr
    0.53
    MessageTagHelper
    0.53
    WriteAttribute
    0.52
    .'</
    0.52
     MOS
    0.51
    Activations Density 37.983%

    No Known Activations