© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12833
    Prev
    Next
    INDEX
    Explanations

    words associated with evaluating the quality or success of something

    oai_token-act-pair · gemini-2.0-flash

    success, relationships, values

    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
    Not in Any Lists

    No Comments

    Negative Logits
    etype
    -0.52
     biến
    -0.52
    出版年
    -0.51
    ebilir
    -0.51
    stances
    -0.46
     tere
    -0.45
    eapp
    -0.45
    entiment
    -0.43
    elv
    -0.43
     geb
    -0.42
    POSITIVE LOGITS
    цездатний
    0.73
    AutoresizingMask
    0.67
    propTypes
    0.65
    AsUp
    0.63
     mouseY
    0.61
    QMetaType
    0.60
     виправивши
    0.59
     AssemblyTitle
    0.59
    SharedCtor
    0.59
    setVerticalGroup
    0.59
    Activations Density 3.107%

    No Known Activations