© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3683
    Prev
    Next
    INDEX
    Explanations

    phrases relating to death, the afterlife, and remembering those who have died and car rallies

    oai_token-act-pair · gemini-2.0-flash

    themes related to death and loss

    np_token-act-pair-logits · gpt-4o-mini

    death and dying words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     deaths
    -0.80
    death
    -0.77
     Deaths
    -0.74
    kill
    -0.72
    afficheront
    -0.71
     morts
    -0.70
     morto
    -0.70
    PerformLayout
    -0.69
    Kill
    -0.69
     killed
    -0.69
    POSITIVE LOGITS
     final
    0.77
     sleep
    0.74
     depart
    0.68
     Sleep
    0.67
     departure
    0.66
     exit
    0.65
     departing
    0.64
    awtextra
    0.64
     rest
    0.63
     leaving
    0.63
    Activations Density 1.444%

    No Known Activations