© 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. 12787
    Prev
    Next
    INDEX
    Explanations

    language typical of medical recommendations and guidelines.

    oai_token-act-pair · gemini-2.0-flash

    medical conditions and terms

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

    medical/scientific guidelines

    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
     tộc
    -0.54
    SharedCtor
    -0.49
    *)&
    -0.47
    Aide
    -0.45
    infeld
    -0.43
    Tikang
    -0.42
     theorist
    -0.42
     ControllerBase
    -0.41
    istad
    -0.41
    Demografía
    -0.40
    POSITIVE LOGITS
     rheumatic
    0.65
     obesity
    0.62
     '\\;'
    0.60
     osteoporosis
    0.56
    localctx
    0.56
    oporosis
    0.56
     Scienti
    0.56
    ITION
    0.56
     otomatig
    0.56
    expandindo
    0.54
    Activations Density 4.074%

    No Known Activations