© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 4359
    Prev
    Next
    INDEX
    Explanations

    mentions of health and the need for awareness and education

    oai_token-act-pair · gemini-2.0-flash

    education

    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
     thiệu
    -0.69
    TouchListener
    -0.55
     препратки
    -0.53
    BindingSource
    -0.52
    Geografi
    -0.52
    IUrlHelper
    -0.52
    AddHtmlAttribute
    -0.51
    NameInMap
    -0.50
     Administrator
    -0.48
     courant
    -0.48
    POSITIVE LOGITS
     education
    2.72
     Education
    2.39
    education
    2.36
    Education
    2.31
     Educ
    2.20
     EDUCATION
    2.19
     educational
    2.19
     educ
    2.14
     educate
    2.13
    Educ
    2.09
    Activations Density 2.529%

    No Known Activations