© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5546
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and ordinal phrases in the context of sports and racing.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BagLayout
    -0.70
    JspWriter
    -0.65
    IsContent
    -0.65
    windowFixed
    -0.60
    StructEnd
    -0.58
     Signalez
    -0.57
     &___
    -0.56
    enderror
    -0.56
     kasarigan
    -0.55
     olsun
    -0.55
    POSITIVE LOGITS
    StoryboardSegue
    0.60
    fromnode
    0.53
    "{
    0.47
    avadoc
    0.46
     physical
    0.46
    Physical
    0.46
    :✨
    0.45
    Gen
    0.44
    찰
    0.44
    Smile
    0.44
    Activations Density 0.834%

    No Known Activations