© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4054
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical conditions, physical therapy, and medical devices

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "support"

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

    support

    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
    AndEndTag
    -0.95
     myſelf
    -0.84
     Jefus
    -0.80
     EnglishChoose
    -0.75
     auffi
    -0.73
     <<<<<<<<<<<<<<
    -0.73
     Efq
    -0.71
     surla
    -0.69
     étoit
    -0.69
     Monfieur
    -0.69
    POSITIVE LOGITS
     support
    0.83
    support
    0.70
     supports
    0.68
     immobili
    0.64
    Support
    0.63
     Support
    0.63
     cast
    0.56
     im
    0.55
     supported
    0.54
     Supports
    0.54
    Activations Density 1.497%

    No Known Activations