© 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. 13609
    Prev
    Next
    INDEX
    Explanations

    verbs related to healthcare quality improvement activities

    oai_token-act-pair · gemini-2.0-flash

    Clinical practice

    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
     transfieras
    -0.80
    Personensuche
    -0.77
     كومونز
    -0.69
    Gweler
    -0.69
    ThroughAttribute
    -0.68
     ujednoznacz
    -0.66
    msgTypes
    -0.64
     VIAF
    -0.63
     ModelRenderer
    -0.62
    Autoritní
    -0.61
    POSITIVE LOGITS
     rounds
    0.65
     Rounds
    0.63
    rounds
    0.57
     education
    0.56
     educational
    0.55
     Mass
    0.52
    textAppearance
    0.50
    Rounds
    0.50
     AUDIT
    0.49
     Self
    0.49
    Activations Density 2.937%

    No Known Activations