© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    mentions of months, especially August, and related words

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "August"

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

    August

    np_max-act-logits · gemini-2.0-flash

    August

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     February
    -0.76
     Christmas
    -0.75
     Omicron
    -0.75
     January
    -0.73
     December
    -0.73
     Xmas
    -0.72
    February
    -0.72
    January
    -0.70
     Valentine
    -0.70
     FEBRUARY
    -0.69
    POSITIVE LOGITS
     Aug
    1.20
    August
    1.20
    Aug
    1.19
     August
    1.18
    AUGUST
    1.05
     AUGUST
    1.05
    august
    1.00
     août
    0.98
     augustus
    0.97
    AUG
    0.95
    Activations Density 0.939%

    No Known Activations