© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7683
    Prev
    Next
    INDEX
    Explanations

    words relating to medical studies or treatment of patients

    oai_token-act-pair · gemini-2.0-flash

    Patients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    GENERATED
    -0.54
     }}"></
    -0.54
     giống
    -0.52
    Demografie
    -0.52
    DebuggerNonUser
    -0.52
     Dä
    -0.51
    లాలు
    -0.51
    اژ
    -0.50
    ★★★★☆
    -0.49
    ngdoc
    -0.49
    POSITIVE LOGITS
     patients
    0.72
    Datuak
    0.69
     clients
    0.58
    WebVitals
    0.57
     ويكيميديا
    0.57
    OGND
    0.56
     Permalink
    0.55
     sufferers
    0.55
     Patients
    0.54
    protoimpl
    0.54
    Activations Density 2.584%

    No Known Activations