© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33544
    Prev
    Next
    INDEX
    Explanations

    death of prominent people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    material
    0.34
    IEF
    0.33
    memorial
    0.33
     memorial
    0.33
    悼
    0.32
    訃
    0.32
     bereaved
    0.32
    olução
    0.32
     DEATH
    0.32
    偿
    0.31
    POSITIVE LOGITS
    休日
    0.30
    edDevice
    0.29
    เหลือ
    0.28
    Sunday
    0.28
    zechos
    0.28
    未来的
    0.27
     zvol
    0.26
    훈
    0.26
     भूगोल
    0.26
     protagonisti
    0.26
    Activations Density 0.002%

    No Known Activations