© 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. 5234
    Prev
    Next
    INDEX
    Explanations

    words within articles or stories about various events and locations

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "under"

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

    under

    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
     betweenstory
    -0.96
    Diwedd
    -0.87
    Datuak
    -0.79
     Roskov
    -0.76
    ValueStyle
    -0.76
    TagMode
    -0.75
    Portale
    -0.75
    protoimpl
    -0.74
     estimés
    -0.73
     Efq
    -0.73
    POSITIVE LOGITS
     under
    3.06
    under
    2.58
    Under
    2.50
     Under
    2.44
     UNDER
    2.17
    UNDER
    2.00
     unter
    1.90
     bajo
    1.79
     sous
    1.74
     sotto
    1.74
    Activations Density 3.023%

    No Known Activations