© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4089
    Prev
    Next
    INDEX
    Explanations

    the word "think"

    oai_token-act-pair · gemini-2.0-flash

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     think
    -2.42
    <bos>
    -2.23
    Think
    -2.14
    think
    -2.06
     Think
    -1.98
     THINK
    -1.84
     thinks
    -1.80
     thinking
    -1.72
    THINK
    -1.58
     thought
    -1.55
    POSITIVE LOGITS
    SizeMode
    0.62
     BUREAU
    0.59
    ⎩
    0.55
    webElementGuid
    0.55
     QLabel
    0.52
     onView
    0.52
    ToBounds
    0.52
    elebr
    0.51
     môn
    0.51
     onAnimation
    0.51
    Activations Density 0.547%

    No Known Activations