© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10528
    Prev
    Next
    INDEX
    Explanations

    tokens that are parts of dates and game scores, and words related to athletic events and holidays

    oai_token-act-pair · gemini-2.0-flash

    Months of the year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     summer
    -1.52
    summer
    -1.41
    Summer
    -1.38
     summertime
    -1.34
     SUMMER
    -1.34
     Summer
    -1.32
    SUMMER
    -1.31
     summers
    -1.27
    June
    -1.15
     July
    -1.14
    POSITIVE LOGITS
     January
    0.81
     Jan
    0.80
     February
    0.75
    FEBRUARY
    0.75
     Feb
    0.73
    January
    0.73
    Jan
    0.69
     enero
    0.68
    February
    0.68
     winter
    0.66
    Activations Density 0.764%

    No Known Activations