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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9629
    Prev
    Next
    INDEX
    Explanations

    words suggestive of celebrations, meals or events, possibly including some non-English words.

    oai_token-act-pair · gemini-2.0-flash

    celebrations and gatherings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     réglable
    -0.58
     Eins
    -0.49
    Defs
    -0.46
     Gegenteil
    -0.46
     vectorielles
    -0.45
     unele
    -0.45
     compréhen
    -0.43
    개
    -0.43
     rosse
    -0.42
     goal
    -0.41
    POSITIVE LOGITS
     DINNER
    1.15
    Dinner
    1.11
     dinner
    1.09
    dinner
    1.07
     Dinner
    1.03
     dinners
    1.00
     Banquet
    0.96
     banquet
    0.95
     supper
    0.94
     meal
    0.91
    Activations Density 0.607%

    No Known Activations