© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18950
    Prev
    Next
    INDEX
    Explanations

    focused sonic waves or electrical current

    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_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    翛
    0.38
     Анаста
    0.38
    ambuf
    0.38
    眝
    0.38
     mengan
    0.37
     logarithm
    0.37
     قیام
    0.37
    更
    0.37
    飜
    0.37
    mandu
    0.36
    POSITIVE LOGITS
     हवा
    0.46
     blasts
    0.45
     lasers
    0.44
     beams
    0.43
     air
    0.42
     bombardment
    0.41
     currents
    0.40
    oblasts
    0.40
     বায়ু
    0.39
     повіт
    0.39
    Activations Density 0.075%

    No Known Activations