© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3507
    Prev
    Next
    INDEX
    Explanations

    the word "typically" and other adverbs of frequency

    oai_token-act-pair · gemini-2.0-flash

    typically

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     zijne
    -0.79
     habet
    -0.78
     enfans
    -0.74
     quæ
    -0.73
     réguli
    -0.72
     rayures
    -0.71
     auroit
    -0.71
     bonté
    -0.70
     ennemi
    -0.69
     réaliste
    -0.69
    POSITIVE LOGITS
     (£
    0.72
    Whilst
    0.71
    ScopeManager
    0.70
     ‘
    0.69
    UserScript
    0.68
    migrationBuilder
    0.65
     Whilst
    0.65
    arised
    0.61
    ropshire
    0.61
    phosa
    0.61
    Activations Density 1.170%

    No Known Activations