© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    words related to religious practices and/or faith in general

    oai_token-act-pair · gemini-2.0-flash

    words related to celebration

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

    celebrate

    np_max-act-logits · gemini-2.0-flash
    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
    abestanden
    -0.61
    PreAuthorize
    -0.50
     незавершена
    -0.45
     ActionResult
    -0.45
    crawl
    -0.43
    ostoma
    -0.43
    addCell
    -0.43
     keten
    -0.43
    abstractmethod
    -0.43
    amo
    -0.42
    POSITIVE LOGITS
     celebrate
    1.02
     celebration
    1.00
     celebrating
    0.91
     Celebrate
    0.90
    celebr
    0.89
    Celebration
    0.88
     Celebration
    0.86
     celebrated
    0.85
     celebrates
    0.84
    celebrate
    0.84
    Activations Density 2.133%

    No Known Activations