© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7132
    Prev
    Next
    INDEX
    Explanations

    snippets of C++ code related to boost tests and tuple manipulation with the namespace "elle::das"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     GenerationType
    -0.72
    IndentedString
    -0.67
    dafx
    -0.67
    StructEnd
    -0.66
    MeasureSpec
    -0.64
    MessageTagHelper
    -0.63
    पया
    -0.62
     الرياضيه
    -0.61
     kaarangay
    -0.60
     BoxFit
    -0.60
    POSITIVE LOGITS
     étoient
    0.62
     avoient
    0.61
     femininas
    0.60
     nød
    0.60
     verksamhet
    0.59
     auroit
    0.59
     negru
    0.59
     militaires
    0.59
     Romains
    0.59
     carottes
    0.58
    Activations Density 21.277%

    No Known Activations