© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10281
    Prev
    Next
    INDEX
    Explanations

    words in legal or cybersecurity contexts describing a sequence of events involving agreements, decisions, and consequences

    oai_token-act-pair · gemini-2.0-flash

    thinking/believing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Obituary
    -0.45
    itele
    -0.40
    ampi
    -0.40
    harma
    -0.39
    กรรม
    -0.38
    openSession
    -0.38
    ipi
    -0.38
    VERSION
    -0.38
     Bur
    -0.37
    zen
    -0.36
    POSITIVE LOGITS
     thinking
    1.91
     believing
    1.82
     assumption
    1.72
     expecting
    1.70
     expectation
    1.68
    thinking
    1.66
     Thinking
    1.59
     belief
    1.58
    assumption
    1.52
    Thinking
    1.50
    Activations Density 3.196%

    No Known Activations