© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9491
    Prev
    Next
    INDEX
    Explanations

    words commonly found in code, like "render", "update", and "process"

    oai_token-act-pair · gemini-2.0-flash

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useParams
    -0.49
     crossorigin
    -0.45
     carre
    -0.44
    ьаж
    -0.42
    noy
    -0.41
     &
    -0.41
    ياب
    -0.41
    
    -0.41
    PageFactory
    -0.40
    ButterKnife
    -0.40
    POSITIVE LOGITS
     purpoſe
    0.83
     myſelf
    0.81
     itſelf
    0.79
     Monfieur
    0.73
     fubject
    0.71
     himſelf
    0.71
     Theſe
    0.69
     themſelves
    0.69
     poffible
    0.68
     leaſt
    0.67
    Activations Density 5.647%

    No Known Activations