© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14732
    Prev
    Next
    INDEX
    Explanations

    years in the 1800s

    oai_token-act-pair · gemini-2.0-flash

    sequences of numbers and proper nouns

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

    8

    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
    ChildScrollView
    -0.77
     تانيه
    -0.68
    MLLoader
    -0.65
     ***!
    -0.62
    urlpatterns
    -0.62
     članak
    -0.61
    adaptiveStyles
    -0.61
    исленность
    -0.61
    apimachinery
    -0.60
     GenerationType
    -0.60
    POSITIVE LOGITS
    chado
    0.52
    istat
    0.50
    ensee
    0.47
    5
    0.46
     P
    0.46
     Sickness
    0.46
    läge
    0.45
     subunits
    0.44
    ondale
    0.44
    himu
    0.44
    Activations Density 0.395%

    No Known Activations