© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14781
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical diagnosis

    oai_token-act-pair · gemini-2.0-flash

    diagnosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     diagnoses
    -0.54
     diagno
    -0.54
     diagnosis
    -0.52
    ereur
    -0.50
     Diagnose
    -0.49
     diagnostic
    -0.49
     diagnosed
    -0.47
     DIAG
    -0.47
    ēr
    -0.45
    ABASES
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.84
    IonicModule
    0.81
     nakalista
    0.79
     ProtoMessage
    0.70
    Personensuche
    0.66
     <=",
    0.63
    دانشنامهٔ
    0.63
     gynhyrchwyd
    0.62
     virginity
    0.60
    ⓘ
    0.60
    Activations Density 3.581%

    No Known Activations