© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13815
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to patient care and medical consultations

    oai_token-act-pair · gemini-2.0-flash

    medical and treatment-related terms

    np_token-act-pair-logits · gpt-4o-mini
    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
    ValueStyle
    -0.84
    ScopeManager
    -0.73
     Efq
    -0.71
    ArgumentParser
    -0.71
    AndEndTag
    -0.70
    @[+][
    -0.70
    StoryboardSegue
    -0.69
    GEBURTSDATUM
    -0.69
     nakalista
    -0.69
    ِّف
    -0.66
    POSITIVE LOGITS
     keper
    0.47
     Y
    0.46
    ahara
    0.44
    geslacht
    0.44
     drug
    0.42
    وق
    0.42
     mole
    0.41
     real
    0.41
    __((
    0.40
     history
    0.40
    Activations Density 7.362%

    No Known Activations