© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11560
    Prev
    Next
    INDEX
    Explanations

    mentions of specific quantities/numbers

    oai_token-act-pair · gemini-2.0-flash

    large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    +#+#
    -0.56
     للمعارف
    -0.56
     constancy
    -0.56
    chond
    -0.55
    InSection
    -0.54
     Sya
    -0.54
     hemo
    -0.53
     academia
    -0.52
     Futter
    -0.52
    complexContent
    -0.51
    POSITIVE LOGITS
     dozen
    0.93
    dozen
    0.83
     dozens
    0.78
     many
    0.76
     dizaine
    0.72
     zahlreichen
    0.70
     cinquante
    0.69
     nombreux
    0.67
     numerous
    0.66
     thousands
    0.66
    Activations Density 1.284%

    No Known Activations