© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7962
    Prev
    Next
    INDEX
    Explanations

    mentions of a limited amount of time

    oai_token-act-pair · gemini-2.0-flash

    Small number quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    PreferredItem
    -0.64
    casila
    -0.62
     BitmapFactory
    -0.61
    autique
    -0.60
     GenerationType
    -0.59
     bogotá
    -0.58
    łaszcza
    -0.58
     joaat
    -0.57
    oretical
    -0.57
    UserScript
    -0.56
    POSITIVE LOGITS
    وعة
    0.59
    Viited
    0.56
     Across
    0.56
    Across
    0.54
     throughout
    0.54
    across
    0.52
    +#+
    0.50
    sequent
    0.49
    Throughout
    0.48
    throughout
    0.48
    Activations Density 1.662%

    No Known Activations