© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12900
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to traditions and customs

    oai_token-act-pair · gemini-2.0-flash

    custom, practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    SpringRunner
    -0.66
     FINANCIAL
    -0.63
    रिक
    -0.61
    Sharper
    -0.60
     Financial
    -0.58
    fileID
    -0.57
    MessageTagHelper
    -0.55
    IRQn
    -0.54
    Financial
    -0.53
     litté
    -0.53
    POSITIVE LOGITS
     practices
    0.90
     practice
    0.86
     tradition
    0.75
    Practices
    0.75
     habits
    0.74
     customs
    0.74
     ritual
    0.74
     rituals
    0.74
     traditions
    0.73
     routine
    0.71
    Activations Density 0.820%

    No Known Activations