© 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. 499
    Prev
    Next
    INDEX
    Explanations

    actions done with enthusiasm or skill

    oai_token-act-pair · gemini-2.0-flash

    with

    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
     незавершена
    -0.84
    Obrázky
    -0.75
    脚注の使い方
    -0.71
     betweenstory
    -0.71
    HasForeignKey
    -0.71
     المعيارى
    -0.69
    ArrowToggle
    -0.68
    ExtendWith
    -0.68
    sizeCache
    -0.65
    GOTREF
    -0.65
    POSITIVE LOGITS
    djangoproject
    0.54
    ^{+}
    0.51
     nguy
    0.48
    جر
    0.47
     bulunabilir
    0.47
     quanto
    0.45
    ith
    0.43
     округ
    0.43
    asal
    0.43
    yeni
    0.43
    Activations Density 10.972%

    No Known Activations