© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15475
    Prev
    Next
    INDEX
    Explanations

    mentions of economic impact or damage from specific events.

    oai_token-act-pair · gemini-2.0-flash

    Negative impact/disruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     WaitForSeconds
    -0.51
    Severity
    -0.48
     Devlin
    -0.46
    Devo
    -0.43
    றி
    -0.43
     retiro
    -0.42
    deckung
    -0.41
    tioned
    -0.41
     MEET
    -0.41
     Pemer
    -0.40
    POSITIVE LOGITS
    hésite
    0.68
    RegressionTest
    0.63
     betweenstory
    0.61
    MLLoader
    0.61
     autorytatywna
    0.59
     propOrder
    0.56
    onActivityResult
    0.56
    ynchronously
    0.55
     समीक्षक
    0.55
    writeFieldEnd
    0.54
    Activations Density 1.414%

    No Known Activations