© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10112
    Prev
    Next
    INDEX
    Explanations

    situations involving medical emergencies and treatment, especially those involving transportation to medical facilities, diagnosis, and recovery.

    oai_token-act-pair · gemini-2.0-flash

    injuries and medical events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للمعارف
    -1.15
    contentLoaded
    -1.09
     betweenstory
    -1.01
     Efq
    -0.99
     Jefus
    -0.99
     myſelf
    -0.97
    oredCriteria
    -0.96
    цездатний
    -0.96
     Monfieur
    -0.94
     doubtnut
    -0.94
    POSITIVE LOGITS
     do
    0.46
     m
    0.46
     tak
    0.44
     انت
    0.44
     vi
    0.44
    do
    0.43
     
    0.43
     pas
    0.43
     pu
    0.42
     being
    0.41
    Activations Density 0.674%

    No Known Activations