© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    short words that commonly occur together, acting almost like a simplified grammar detector

    oai_token-act-pair · gemini-2.0-flash

    Diverse environments/establishments

    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
    Tē
    -0.55
     муніципалі
    -0.54
     Приступљено
    -0.49
     PropertyChanged
    -0.48
    apimachinery
    -0.47
    djangoproject
    -0.47
    ']?>
    -0.47
    Chham
    -0.47
    UnusedPrivate
    -0.47
    useNewUrlParser
    -0.47
    POSITIVE LOGITS
     run
    0.75
     seed
    0.59
     Run
    0.56
    coltà
    0.55
     CreateTagHelper
    0.55
    run
    0.54
     devemos
    0.52
    ScopeManager
    0.52
    Run
    0.51
     marinho
    0.51
    Activations Density 2.641%

    No Known Activations