© 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. 6111
    Prev
    Next
    INDEX
    Explanations

    delimiters, conditional statements, and sizing

    oai_token-act-pair · gemini-2.0-flash

    not

    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
     endwhile
    -0.66
     propOrder
    -0.62
     متعلقه
    -0.57
     @"/
    -0.54
     ujednoznacz
    -0.54
     protoimpl
    -0.54
    urably
    -0.53
    CppMethod
    -0.52
     تضيفلها
    -0.51
    queryInterface
    -0.50
    POSITIVE LOGITS
     not
    1.66
     nicht
    1.38
     não
    1.31
     niet
    1.29
    not
    1.23
     wasn
    1.23
     не
    1.18
     NOT
    1.17
     isn
    1.17
     Not
    1.17
    Activations Density 2.219%

    No Known Activations