© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1833
    Prev
    Next
    INDEX
    Explanations

    words associated with strong opinions and forecasts

    oai_token-act-pair · gemini-2.0-flash

    Words ending in "s"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ActivityCompat
    -0.47
     Consejo
    -0.47
    lında
    -0.47
     suo
    -0.46
    >
    -0.46
    )))),
    -0.46
    </b>
    -0.46
    palen
    -0.45
    passt
    -0.45
     Daily
    -0.44
    POSITIVE LOGITS
    ContentAsync
    0.92
    parsedMessage
    0.84
    PerformLayout
    0.78
    IsContent
    0.75
    setVerticalGroup
    0.74
     myſelf
    0.72
     ModelExpression
    0.67
     ویکی‌پدیا
    0.67
     surla
    0.66
     AssemblyProduct
    0.65
    Activations Density 5.842%

    No Known Activations