© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3611
    Prev
    Next
    INDEX
    Explanations

    locations in Wales

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.48
    NameInMap
    -0.48
    ktı
    -0.47
     ब्रेकडाउन
    -0.46
     ujednoznacz
    -0.46
    rófono
    -0.44
    ȝ
    -0.43
     Welsh
    -0.43
    ukunft
    -0.43
     vastaan
    -0.43
    POSITIVE LOGITS
    wpi
    0.61
    mtrl
    0.59
     ویکی‌پدیای
    0.57
    ThroughAttribute
    0.56
     JADX
    0.55
    TabLayout
    0.53
    PreExecute
    0.53
     getItemCount
    0.53
     Barbuda
    0.52
    GetAsync
    0.52
    Activations Density 29.767%

    No Known Activations