© 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. 5055
    Prev
    Next
    INDEX
    Explanations

    words related to utility and housing companies, or research and funding and companies.

    oai_token-act-pair · gemini-2.0-flash

    NPower

    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
    />";
    -0.71
    makeConstraints
    -0.69
    ...");
    -0.67
     **/
    -0.66
    .";
    -0.65
    NUMX
    -0.62
    !")
    -0.62
    .",
    -0.61
    "]();
    -0.61
     $_"
    -0.60
    POSITIVE LOGITS
    BagLayout
    0.53
    SharedCtor
    0.52
     numerus
    0.49
     AppComponent
    0.47
    tagext
    0.47
    AndEndTag
    0.47
    mybatisplus
    0.46
    PreferredItem
    0.46
     iprot
    0.45
    borderSide
    0.45
    Activations Density 2.662%

    No Known Activations