© 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
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16411
    Prev
    Next
    INDEX
    Explanations

    special relativity

    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_15_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
    ات
    0.20
     (
    0.19
    时不
    0.18
     cells
    0.18
    iop
    0.18
    िश
    0.17
     thermodynamics
    0.17
     vowels
    0.17
     inducible
    0.17
    치
    0.17
    POSITIVE LOGITS
     Raila
    0.21
    ຕໍ່
    0.21
     ещё
    0.20
     Юрий
    0.20
    usaha
    0.19
    ນີ້
    0.19
     lakini
    0.19
     какой
    0.18
    nagar
    0.18
     ფედერ
    0.18
    Activations Density 0.007%

    No Known Activations