© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4686
    Prev
    Next
    INDEX
    Explanations

    newspaper article metadata and image credits

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or keywords

    np_token-act-pair-logits · gpt-4o-mini

    News articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    contentLoaded
    -0.63
    DockStyle
    -0.57
    WebVitals
    -0.50
    GEBURTSDATUM
    -0.50
     Audiodateien
    -0.49
    UnusedPrivate
    -0.48
    Uninitialized
    -0.44
    AsUp
    -0.44
    reactivex
    -0.43
     незавершена
    -0.42
    POSITIVE LOGITS
     препратки
    0.74
     StatefulWidget
    0.62
    jelder
    0.60
    NewLabel
    0.59
     Active
    0.59
    protoimpl
    0.59
     HasFactory
    0.58
    Active
    0.57
     Kuta
    0.57
    kmal
    0.56
    Activations Density 0.751%

    No Known Activations