© 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-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234249
    Prev
    Next
    INDEX
    Explanations

    death of monarch

    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_32_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
    泍
    0.43
     surprises
    0.42
     animasi
    0.42
     actualizaciones
    0.41
     SIRT
    0.41
     EDUCATION
    0.40
     त्वरित
    0.40
     Pork
    0.39
    갱
    0.39
     తి
    0.39
    POSITIVE LOGITS
     boom
    0.43
    urdy
    0.36
     wob
    0.36
    集
    0.36
     gathered
    0.36
     bloc
    0.36
     collection
    0.35
     Hul
    0.35
     mon
    0.35
    boom
    0.35
    Activations Density 0.001%

    No Known Activations