© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10717
    Prev
    Next
    INDEX
    Explanations

    words related to violent crime, death, or arrests

    oai_token-act-pair · gemini-2.0-flash

    death

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     death
    -2.45
    death
    -2.14
     Death
    -2.03
    Death
    -1.95
     DEATH
    -1.93
    DEATH
    -1.74
     muerte
    -1.37
     morte
    -1.35
     deaths
    -1.26
     śmierci
    -1.20
    POSITIVE LOGITS
     initComponents
    0.63
     snippetHide
    0.57
     pinulongan
    0.56
    ponses
    0.56
    basicConfig
    0.52
    orsk
    0.52
     shear
    0.46
     referenties
    0.45
    IsInitialized
    0.45
     berle
    0.45
    Activations Density 5.763%

    No Known Activations