© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170212
    Prev
    Next
    INDEX
    Explanations

    holding back or maintaining possession

    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_20_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
     tetra
    0.24
     cancellations
    0.22
    保管
    0.22
     conspired
    0.22
     sm
    0.22
    Cancellation
    0.21
     armazenamento
    0.21
    积累
    0.21
    瞓
    0.21
     estancia
    0.21
    POSITIVE LOGITS
     hatta
    0.26
     dàng
    0.25
     pero
    0.24
    antages
    0.23
    aniy
    0.23
    ituus
    0.23
    anch
    0.23
    ό
    0.23
    तात
    0.22
     bahkan
    0.22
    Activations Density 0.002%

    No Known Activations