© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1248
    Prev
    Next
    INDEX
    Explanations

    references to holidays, especially Christmas and Valentine's Day, and related terms such as gifts

    oai_token-act-pair · gemini-2.0-flash

    holidays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    addContainerGap
    -0.81
    ysty
    -0.71
    DebuggerNonUser
    -0.68
     HasFactory
    -0.67
    TagMode
    -0.65
    opsida
    -0.64
    ⓧ
    -0.64
    MLLoader
    -0.64
    RegressionTest
    -0.61
     كومونز
    -0.60
    POSITIVE LOGITS
     festive
    0.56
     holiday
    0.49
     festivities
    0.46
    Christmas
    0.45
     celebrating
    0.45
    seits
    0.44
     seasonal
    0.44
    Thanksgiving
    0.44
    bibliography
    0.43
     Festive
    0.43
    Activations Density 0.949%

    No Known Activations