© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11648
    Prev
    Next
    INDEX
    Explanations

    statements about community awareness of a condition

    oai_token-act-pair · gemini-2.0-flash

    awareness

    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
     conscious
    -2.03
     awareness
    -1.99
    Awareness
    -1.95
     Awareness
    -1.94
    awareness
    -1.86
    Conscious
    -1.81
     consciousness
    -1.81
     Conscious
    -1.80
    conscious
    -1.64
     Consciousness
    -1.57
    POSITIVE LOGITS
    mobileqq
    0.61
     Waray
    0.56
    LogFactory
    0.52
     con
    0.52
     vě
    0.48
    testify
    0.48
    fflush
    0.46
    fortawesome
    0.46
     تضيفلها
    0.45
    DebuggerStep
    0.45
    Activations Density 1.319%

    No Known Activations