© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16332
    Prev
    Next
    INDEX
    Explanations

    first-person introductions giving a name and stating goals or activities

    oai_token-act-pair · gemini-2.0-flash

    is and commas

    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
    Negative Logits
    enscha
    -0.66
    wikidata
    -0.61
    UserScript
    -0.60
    PRWEB
    -0.60
     severity
    -0.60
     Wirtschafts
    -0.60
    criptures
    -0.59
     באמצ
    -0.59
    zarchiwizowane
    -0.59
    ksessa
    -0.59
    POSITIVE LOGITS
    RectangleBorder
    0.50
    RunWith
    0.47
    typeorm
    0.44
     $("<
    0.42
    Geografía
    0.40
    RuleContext
    0.38
    MenuInflater
    0.38
     الحره
    0.38
     BoxDecoration
    0.37
    AddTagHelper
    0.35
    Activations Density 3.208%

    No Known Activations