© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3682
    Prev
    Next
    INDEX
    Explanations

    the letter "a" in different code and natural language contexts

    oai_token-act-pair · gemini-2.0-flash

    Programming code and text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Upon
    -0.59
     selamat
    -0.59
     supérieure
    -0.56
     Upon
    -0.56
     refusé
    -0.54
    nahm
    -0.53
     supérieures
    -0.53
     supérieurs
    -0.53
     Milner
    -0.53
     at
    -0.52
    POSITIVE LOGITS
    <bos>
    0.97
     ujednoznacz
    0.79
     propOrder
    0.75
     محفوظة
    0.69
     चीज़ों
    0.64
    WriteTagHelper
    0.63
    はじめに
    0.60
     Савезне
    0.60
    OGND
    0.60
     estekak
    0.59
    Activations Density 1.581%

    No Known Activations