© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15435
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate opinions and commentary on legal or policy matters.

    oai_token-act-pair · gemini-2.0-flash

    say "that"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    EndContext
    -0.94
    ArgsConstructor
    -0.90
    GEBURTSDATUM
    -0.85
     nahilalakip
    -0.79
     للمعارف
    -0.79
    tonode
    -0.78
    RegressionTest
    -0.77
     typelib
    -0.76
    ThroughAttribute
    -0.76
    AddTagHelper
    -0.75
    POSITIVE LOGITS
     that
    0.76
     
    0.56
     or
    0.52
     —
    0.50
     O
    0.50
     through
    0.47
     al
    0.47
     ==
    0.47
    —
    0.47
    es
    0.45
    Activations Density 1.991%

    No Known Activations