© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154344
    Prev
    Next
    INDEX
    Explanations

    "each" or "some"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    瓦
    0.38
    ハー
    0.38
     merges
    0.38
     Entrance
    0.37
    entrance
    0.36
    য়িক
    0.36
     거죠
    0.36
    oxine
    0.35
    ুক
    0.35
    ‏:‏
    0.35
    POSITIVE LOGITS
     इनमें
    0.77
     उनमें
    0.77
    其中的
    0.68
    其中
    0.61
     chacun
    0.55
     among
    0.55
     alternatively
    0.54
     dintre
    0.53
     cualquiera
    0.52
     chacune
    0.50
    Activations Density 0.001%

    No Known Activations