© 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. 550
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to violence, killing, and aggression

    oai_token-act-pair · gemini-2.0-flash

    violence

    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
    tram
    -0.49
    HORE
    -0.46
    
    -0.44
    watermark
    -0.43
    defs
    -0.43
    cadre
    -0.42
     Parkes
    -0.41
    clearTimeout
    -0.41
    悔
    -0.41
     Aldrich
    -0.41
    POSITIVE LOGITS
     violence
    1.26
     violent
    1.14
    Violence
    1.12
    violence
    1.09
     Violence
    1.05
     violento
    1.00
     Violent
    1.00
    Violent
    0.98
     violência
    0.97
    violent
    0.94
    Activations Density 2.229%

    No Known Activations