© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 782
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to historical governance and death

    oai_token-act-pair · gemini-2.0-flash

    death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.16
    death
    -1.95
     Death
    -1.90
    Death
    -1.84
     DEATH
    -1.77
    DEATH
    -1.63
     deaths
    -1.27
     muerte
    -1.26
     смерти
    -1.17
     Deaths
    -1.17
    POSITIVE LOGITS
     later
    0.41
    nonce
    0.41
     Later
    0.40
    RA
    0.40
    Later
    0.40
    ra
    0.39
     die
    0.38
    を増
    0.37
    vias
    0.37
     selanjutnya
    0.37
    Activations Density 15.995%

    No Known Activations