© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8464
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to diseases, medical procedures, and symptoms

    oai_token-act-pair · gemini-2.0-flash

    inflammation/disease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     osteoporosis
    -1.27
     stamens
    -1.27
     psoriasis
    -1.23
     cerebellum
    -1.19
     propOrder
    -1.18
     anaemia
    -1.16
     cirrhosis
    -1.15
     plagioclase
    -1.15
     anſ
    -1.14
     rheumatism
    -1.14
    POSITIVE LOGITS
     my
    0.73
     por
    0.64
     par
    0.62
     som
    0.62
     int
    0.61
     Int
    0.60
     cap
    0.58
     and
    0.57
     a
    0.55
     per
    0.55
    Activations Density 4.151%

    No Known Activations