© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15275
    Prev
    Next
    INDEX
    Explanations

    code snippets or data formats, especially those involving JSON, models, and cursors

    oai_token-act-pair · gemini-2.0-flash

    json

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    /*
    -0.63
    !("{
    -0.59
     autorytatywna
    -0.59
    /**
    -0.56
    waitKey
    -0.56
     departed
    -0.55
    Хьажоргаш
    -0.55
    Referanser
    -0.55
    WEBPACK
    -0.53
     nahilalakip
    -0.53
    POSITIVE LOGITS
    CreateModel
    0.51
    arXiv
    0.49
    Arrive
    0.47
    */)
    0.47
    arrive
    0.46
     Institute
    0.45
    PRNewswire
    0.44
     Pelt
    0.43
    createComponent
    0.42
    sic
    0.42
    Activations Density 4.127%

    No Known Activations