© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15783
    Prev
    Next
    INDEX
    Explanations

    language related to medical research studies and their results

    oai_token-act-pair · gemini-2.0-flash

    medications/drugs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     متعلقه
    -0.78
    WriteTagHelper
    -0.69
    ThroughAttribute
    -0.59
    AnimationsModule
    -0.58
     Carn
    -0.57
    esModule
    -0.56
    UnsafeEnabled
    -0.55
    WithIOException
    -0.51
     Pilate
    -0.50
    Personendaten
    -0.49
    POSITIVE LOGITS
     medication
    1.20
     drugs
    1.19
     drug
    1.16
     Drugs
    1.13
     pills
    1.11
    Drugs
    1.10
     meds
    1.10
    medication
    1.09
    drug
    1.06
    drugs
    1.05
    Activations Density 10.142%

    No Known Activations