© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 430
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "moment" and often the word "now"

    oai_token-act-pair · gemini-2.0-flash

    moment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    期刊论文
    -0.73
     betweenstory
    -0.64
     مشين
    -0.58
     виправивши
    -0.58
    iastes
    -0.57
    出版年
    -0.57
    món
    -0.56
    Vaata
    -0.56
    
    -0.55
     DialogInterface
    -0.55
    POSITIVE LOGITS
     currently
    1.13
     presently
    1.02
    currently
    0.99
    Currently
    0.96
     current
    0.95
     Currently
    0.92
     Presently
    0.85
     CURRENT
    0.84
    CURRENT
    0.82
    current
    0.81
    Activations Density 0.918%

    No Known Activations