© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 11588
    Prev
    Next
    INDEX
    Explanations

    words related to killing or murder

    oai_token-act-pair · gemini-2.0-flash

    murder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     effect
    -1.00
    ".
    
    -0.96
    ).
    
    -0.95
    .";
    
    -0.88
    )*/
    -0.84
    ).}
    -0.83
    ).</
    -0.81
    leſs
    -0.81
    "):
    
    -0.81
    $.
    
    -0.81
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     légère
    0.71
     polaire
    0.70
     colorés
    0.70
     femei
    0.68
     silêncio
    0.68
     segredo
    0.67
     beijo
    0.67
     appelés
    0.67
     récente
    0.67
    Activations Density 1.925%

    No Known Activations