© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    mentions of joy and waking up in the morning, especially when associated with happiness and brightness.

    oai_token-act-pair · gemini-2.0-flash

    Positive emotions

    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
     bright
    -1.23
     Bright
    -1.14
     cheerful
    -1.13
     BRIGHT
    -1.12
     brighter
    -1.05
    Bright
    -1.04
    bright
    -1.04
     brightened
    -0.97
    BRIGHT
    -0.96
     brighten
    -0.95
    POSITIVE LOGITS
     فريبيس
    0.54
    /*++
    0.52
    busch
    0.50
    🔙
    0.50
    CDU
    0.50
     estimés
    0.49
    ImageContext
    0.49
    ########.
    0.48
    usz
    0.47
    lear
    0.47
    Activations Density 3.050%

    No Known Activations