© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15570
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical treatment and analysis

    oai_token-act-pair · gemini-2.0-flash

    treatment

    np_max-act · gemini-2.0-flash

    Treatment Method used: 1, reason: repeated "Treatment" tokens, explanation: Treatment

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Adsorption
    -1.29
     Deformation
    -1.24
     Optimization
    -1.24
     Inhibition
    -1.22
     Estimation
    -1.19
     Reactivity
    -1.18
     Formatting
    -1.18
     Stimulation
    -1.17
     Negotiation
    -1.16
     Forecasting
    -1.16
    POSITIVE LOGITS
     process
    0.98
     development
    0.88
     information
    0.88
     application
    0.85
     analysis
    0.83
     system
    0.82
     procedure
    0.82
     action
    0.81
     use
    0.77
     performance
    0.77
    Activations Density 7.000%

    No Known Activations