© 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. 15538
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are technical terms from different fields

    oai_token-act-pair · gemini-2.0-flash

    certificates

    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
    <bos>
    -0.67
    contentLoaded
    -0.63
    ))->
    -0.57
    avaient
    -0.55
     /\.
    -0.55
    SuspendLayout
    -0.54
     /\.(
    -0.53
    IonicModule
    -0.51
     jScrollPane
    -0.51
     secas
    -0.51
    POSITIVE LOGITS
    Smarty
    0.58
    wapV
    0.54
    Personensuche
    0.53
     poveznice
    0.50
     torchvision
    0.50
    TestingModule
    0.49
    šanu
    0.49
     Kans
    0.47
    ruptedException
    0.47
    vereignty
    0.45
    Activations Density 4.818%

    No Known Activations