© 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. 11879
    Prev
    Next
    INDEX
    Explanations

    references to cell culture and lab experiment materials

    oai_token-act-pair · gemini-2.0-flash

    specific identifiers or technical terms

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

    cell culture experiments

    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
    _))
    -0.50
    arang
    -0.50
    appartamento
    -0.49
    🏾
    -0.49
    rehensible
    -0.49
    uesa
    -0.48
     TOUR
    -0.48
    Lähteet
    -0.48
    PhysRevD
    -0.47
     camps
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.88
     дописавши
    0.73
    ValueGeneration
    0.68
     للاسماء
    0.65
     تضيفلها
    0.63
    GEBURTSDATUM
    0.62
    اریخ
    0.62
    featureID
    0.60
    Portály
    0.59
    ValueStyle
    0.57
    Activations Density 1.560%

    No Known Activations