© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer or patient satisfaction

    oai_token-act-pair · gemini-2.0-flash

    happiness/satisfaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     GenerationType
    -0.68
    ::$_
    -0.67
     BoxDecoration
    -0.67
     للاسماء
    -0.64
     AssemblyTitle
    -0.63
     <>",
    -0.63
     purpoſe
    -0.63
     ſte
    -0.61
    rotech
    -0.61
     ſche
    -0.60
    POSITIVE LOGITS
     happy
    2.09
     satisfied
    1.88
    Happy
    1.79
     Happy
    1.78
    happy
    1.76
     satisfaction
    1.76
     HAPPY
    1.63
     Satisfied
    1.61
    HAPPY
    1.55
    satisfied
    1.52
    Activations Density 1.141%

    No Known Activations