© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8335
    Prev
    Next
    INDEX
    Explanations

    multiple things; it seems to trigger for certain proper nouns, especially people's names, and potentially scientific, political, or military references.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     internetowa
    -0.58
     مواليد
    -0.54
    endforeach
    -0.52
    complexType
    -0.52
    Datuak
    -0.52
     simplifié
    -0.50
     DevExpress
    -0.50
    Παραπομπές
    -0.50
    localctx
    -0.49
    ividu
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    IUrlHelper
    0.66
     kasarigan
    0.62
     Italijani
    0.60
    OfWork
    0.56
    ########.
    0.55
    +#+#
    0.51
    ollectionView
    0.50
     AssemblyCompany
    0.50
    KommentareTeilen
    0.49
    Activations Density 0.662%

    No Known Activations