© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 410
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death, injury, or loss

    oai_token-act-pair · gemini-2.0-flash

    Death and casualties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     death
    -1.44
     died
    -1.39
     dead
    -1.26
    death
    -1.22
     Death
    -1.19
     deaths
    -1.15
     dying
    -1.11
     deceased
    -1.10
    dead
    -1.10
    Death
    -1.09
    POSITIVE LOGITS
    DebuggerNonUser
    0.60
    principalColumn
    0.57
     transférez
    0.57
    xiety
    0.53
    BeginContext
    0.53
     kaarangay
    0.49
    MeasureSpec
    0.49
     stanovnika
    0.48
    OpenHelper
    0.47
    loom
    0.47
    Activations Density 0.393%

    No Known Activations