© 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. 7998
    Prev
    Next
    INDEX
    Explanations

    mentions of "gap" in a technical context

    oai_token-act-pair · gemini-2.0-flash

    gap

    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
    Negative Logits
     gap
    -2.97
     Gap
    -2.52
    gap
    -2.52
    Gap
    -2.45
     gaps
    -2.39
     Gaps
    -2.20
    gaps
    -2.05
     GAP
    -1.92
    GAP
    -1.68
    갭
    -1.13
    POSITIVE LOGITS
     суток
    0.46
    baguna
    0.45
     Versuch
    0.44
    Bukan
    0.44
    EndProject
    0.44
    fjspx
    0.44
     tempi
    0.43
    bcryptjs
    0.43
     Else
    0.42
    utnik
    0.42
    Activations Density 0.700%

    No Known Activations