© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10146
    Prev
    Next
    INDEX
    Explanations

    descriptions of amounts of energy, especially when dealing with explosions

    oai_token-act-pair · gemini-2.0-flash

    Nuclear bombs/weapons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    merkung
    -0.47
     gainera
    -0.47
    Grape
    -0.45
     cố
    -0.44
    byshev
    -0.43
    idc
    -0.43
    innan
    -0.42
    埠
    -0.42
     fidé
    -0.42
     sportifs
    -0.41
    POSITIVE LOGITS
     atomic
    0.83
     nuclear
    0.81
     Nagasaki
    0.78
     dropped
    0.74
     Atomic
    0.73
     Hiroshima
    0.71
    nuclear
    0.71
     bomb
    0.70
    twimg
    0.68
     bombs
    0.67
    Activations Density 0.922%

    No Known Activations