© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15021
    Prev
    Next
    INDEX
    Explanations

    variations of the word "think"

    oai_token-act-pair · gemini-2.0-flash

    think

    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
     thought
    -1.43
     Thought
    -1.20
    Thought
    -1.16
    thought
    -1.15
     think
    -1.04
     thinking
    -1.03
     THOUGHT
    -1.02
     Thinking
    -0.98
     Think
    -0.94
    Think
    -0.94
    POSITIVE LOGITS
    ValueStyle
    0.61
    ivir
    0.57
    iNdEx
    0.52
     تضيفلها
    0.51
    addCriterion
    0.51
    WebVitals
    0.51
    cyklopedia
    0.51
    InputBorder
    0.50
    principalColumn
    0.49
     wireType
    0.49
    Activations Density 1.182%

    No Known Activations