© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10499
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related words of authority

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'think'

    np_token-act-pair-logits · gpt-4o-mini

    variations of "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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     heart
    -0.82
    heart
    -0.73
     hearts
    -0.72
    hearts
    -0.72
     Heart
    -0.68
    Heart
    -0.65
     HEART
    -0.62
     corazón
    -0.58
    zene
    -0.54
    odotus
    -0.54
    POSITIVE LOGITS
     think
    2.00
     thought
    1.82
     thinks
    1.80
     Think
    1.76
    Think
    1.73
    think
    1.72
     THINK
    1.64
     Thought
    1.59
    thought
    1.52
     thinking
    1.49
    Activations Density 1.931%

    No Known Activations