© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5017
    Prev
    Next
    INDEX
    Explanations

    code-like text, including filenames, function definitions, directives, and possibly formatted data enclosed in specific delimiters

    oai_token-act-pair · gemini-2.0-flash

    code and data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Hentet
    -0.52
    AsUp
    -0.42
     kaynağından
    -0.41
     aidant
    -0.41
    løs
    -0.40
    Enllaces
    -0.40
     free
    -0.40
    кож
    -0.39
    Външни
    -0.39
     earlier
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.89
    afficheront
    0.83
     disambiguazione
    0.82
     JADX
    0.81
    tvguidetime
    0.78
     متعلقه
    0.77
    Hochspringen
    0.73
     estekak
    0.72
     snippetHide
    0.71
    Tikang
    0.69
    Activations Density 4.747%

    No Known Activations