© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14215
    Prev
    Next
    INDEX
    Explanations

    mentions of a patient's condition, and its diagnosis and treatment over time.

    oai_token-act-pair · gemini-2.0-flash

    medical treatments and diagnosis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Treatments
    -0.90
     Treatment
    -0.85
    Treatment
    -0.84
    treatment
    -0.84
    Treatments
    -0.82
     treatments
    -0.81
     TREATMENT
    -0.79
     treatment
    -0.78
    TREATMENT
    -0.78
     remedy
    -0.77
    POSITIVE LOGITS
     ModelExpression
    0.58
    ்த்த
    0.53
     invokingState
    0.53
     rischio
    0.50
    NewReader
    0.49
    SuccessListener
    0.47
     miljoner
    0.47
    InputModule
    0.44
     مواليد
    0.44
    sidenav
    0.44
    Activations Density 2.302%

    No Known Activations