© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8009
    Prev
    Next
    INDEX
    Explanations

    the word "advance" as a verb (including conjugated forms)

    oai_token-act-pair · gemini-2.0-flash

    advance

    np_max-act · gemini-2.0-flash

    advance

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
     advance
    -2.77
     advanced
    -2.75
     Advance
    -2.58
    advanced
    -2.53
    advance
    -2.52
     Advanced
    -2.52
    Advance
    -2.50
    Advanced
    -2.44
     ADVANCED
    -2.19
     ADVANCE
    -2.19
    POSITIVE LOGITS
    EndInit
    0.56
    HandlerContext
    0.54
    ronesia
    0.51
    lorum
    0.49
     Timoteo
    0.48
    saraba
    0.48
     الدولى
    0.47
    IsSet
    0.47
     SUA
    0.47
    numerusform
    0.47
    Activations Density 0.458%

    No Known Activations