© 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. 4005
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with news reporting, especially related to current events and people

    oai_token-act-pair · gemini-2.0-flash

    Daily Mail articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cristo
    -0.54
    qt
    -0.49
    AddTagHelper
    -0.48
    fromnode
    -0.47
    existsSync
    -0.47
     faptul
    -0.46
     vectorielles
    -0.46
    زيد
    -0.46
    Diwedd
    -0.46
     Baby
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.63
    RTLR
    0.63
    rungsseite
    0.62
    BeginContext
    0.58
    UnitTesting
    0.57
    ResumeLayout
    0.56
    EndInit
    0.56
    NameInMap
    0.56
    complexContent
    0.54
     onCreateView
    0.54
    Activations Density 0.537%

    No Known Activations