© 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. 8237
    Prev
    Next
    INDEX
    Explanations

    text emphasizing the importance of some concept or action

    oai_token-act-pair · gemini-2.0-flash

    important

    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
    Negative Logits
     disambiguazione
    -0.61
    sizeCache
    -0.60
    脚注の使い方
    -0.56
     []:
    -0.55
     ostavi
    -0.52
     EconPapers
    -0.50
    NameInMap
    -0.49
     free
    -0.49
    addGap
    -0.47
    Reentrant
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.84
     Monfieur
    0.72
     Jefus
    0.69
    expandindo
    0.66
     raiſ
    0.61
     mergeFrom
    0.59
     Theſe
    0.57
     estekak
    0.56
     AspNetCore
    0.55
     revelado
    0.55
    Activations Density 0.771%

    No Known Activations