© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10397
    Prev
    Next
    INDEX
    Explanations

    words associated with medical procedures and medications being administered to a patient

    oai_token-act-pair · gemini-2.0-flash

    injection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCompany
    -0.71
     >=",
    -0.63
    sizeCache
    -0.63
     BoxDecoration
    -0.61
    AlterField
    -0.59
     spazz
    -0.58
     }}"></
    -0.58
    Eloquent
    -0.56
     expropri
    -0.53
     Coefficient
    -0.52
    POSITIVE LOGITS
     injection
    1.37
     inject
    1.33
     Injection
    1.22
     injecting
    1.16
    injection
    1.16
     Inject
    1.13
     injected
    1.12
     injections
    1.10
    inject
    1.08
    Injection
    1.01
    Activations Density 1.523%

    No Known Activations