© 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. 5189
    Prev
    Next
    INDEX
    Explanations

    descriptors of things, people, places or events (e.g. "particularly noted for").

    oai_token-act-pair · gemini-2.0-flash

    well-known

    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
     typelib
    -0.79
    Tikang
    -0.77
     Numerade
    -0.74
    rungsseite
    -0.73
    oredCriteria
    -0.72
     فريبيس
    -0.71
    UserScript
    -0.70
    setVerticalGroup
    -0.70
    WebVitals
    -0.69
    CloseOperation
    -0.69
    POSITIVE LOGITS
     because
    0.46
    because
    0.45
     expédi
    0.43
    経緯
    0.43
    Because
    0.42
    ďaka
    0.42
    zusetzen
    0.41
     Hinblick
    0.40
     vanwege
    0.40
    ENNE
    0.40
    Activations Density 1.409%

    No Known Activations