© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3998
    Prev
    Next
    INDEX
    Explanations

    the word "large" and words that co-occur with it, along with some common English words.

    oai_token-act-pair · gemini-2.0-flash

    large, huge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     itſelf
    -0.78
    ſelves
    -0.75
    ThroughAttribute
    -0.74
     ſche
    -0.71
     Efq
    -0.71
     resourceCulture
    -0.70
     ſeveral
    -0.69
     ſmall
    -0.68
     pleaſure
    -0.67
     Reſ
    -0.65
    POSITIVE LOGITS
     quan
    0.61
     number
    0.55
     ↑
    0.55
    qrstuvwxyz
    0.52
    obre
    0.52
     amount
    0.49
    edly
    0.49
     amounts
    0.47
    URLException
    0.47
    綜合報導
    0.47
    Activations Density 9.816%

    No Known Activations