© 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. 281
    Prev
    Next
    INDEX
    Explanations

    words related to expertise in a field

    oai_token-act-pair · gemini-2.0-flash

    publishing and organizations

    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
     bla
    -0.49
    bla
    -0.47
    グラム
    -0.46
    envolvimento
    -0.45
     cerveja
    -0.44
     активности
    -0.44
    existsSync
    -0.44
     rå
    -0.43
    objc
    -0.42
    Compat
    -0.41
    POSITIVE LOGITS
     Baillargeon
    0.66
    Gambas
    0.62
     autorytatywna
    0.61
    __':
    0.58
     renom
    0.58
    )}_
    0.57
    Beloved
    0.57
    +<
    0.56
     незавершена
    0.56
     constexpr
    0.55
    Activations Density 0.930%

    No Known Activations