© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 609
    Prev
    Next
    INDEX
    Explanations

    questions using 'can', 'would', 'should', 'could' and asking for permission or possibility

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    =$?
    -0.54
    Kaynakça
    -0.53
     dacă
    -0.48
     foon
    -0.47
     daca
    -0.46
    saurus
    -0.45
     QtCore
    -0.45
     ？
    -0.45
     siis
    -0.44
     når
    -0.43
    POSITIVE LOGITS
    Tikang
    0.81
     @"/
    0.77
     they
    0.69
    TagHelper
    0.68
     you
    0.65
    IsMutable
    0.62
     "..\..\
    0.61
     &___
    0.59
    usercontent
    0.59
     Wikimedijinoj
    0.58
    Activations Density 2.943%

    No Known Activations