© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13560
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "well" in the context of well-being or doing well

    oai_token-act-pair · gemini-2.0-flash

    Employee well-being

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Being
    -1.47
     being
    -1.41
     Being
    -1.40
    being
    -1.33
     BEING
    -1.26
     étant
    -0.94
     sendo
    -0.79
     bein
    -0.74
    être
    -0.68
     beings
    -0.65
    POSITIVE LOGITS
    OGND
    0.56
    Халык
    0.55
     UserDao
    0.54
    localVar
    0.54
    getKeyCode
    0.54
    LEADING
    0.52
    getDoctrine
    0.52
    mentaux
    0.52
     andata
    0.52
    getClassLoader
    0.51
    Activations Density 6.010%

    No Known Activations