© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8027
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to fluorescence and quantum sensors

    oai_token-act-pair · gemini-2.0-flash

    fluorescence and light emission

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    
    -0.55
    Filmografie
    -0.45
     transmis
    -0.45
    Примечания
    -0.44
     conductor
    -0.43
     przewod
    -0.43
     bezeichneter
    -0.41
     transmission
    -0.41
     break
    -0.41
    曖昧さ回避
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.79
    expandindo
    0.68
     Emission
    0.65
     Excited
    0.64
     Italijani
    0.62
    mingen
    0.61
     Rotten
    0.60
    Emission
    0.60
    Excited
    0.60
    TypedDataSet
    0.59
    Activations Density 2.608%

    No Known Activations