© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161460
    Prev
    Next
    INDEX
    Explanations

    ice age ended

    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_31_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
    閎
    0.42
    ниц
    0.40
    ampang
    0.39
    যেন
    0.39
    licted
    0.39
    داث
    0.39
     toys
    0.38
     COLLEGE
    0.38
     kapital
    0.38
     निर्यात
    0.38
    POSITIVE LOGITS
    Splash
    0.42
     Splash
    0.41
     flow
    0.38
    樽
    0.38
     строку
    0.38
    NAP
    0.38
     Atmosphere
    0.37
    捞
    0.37
     repeated
    0.37
     Gases
    0.37
    Activations Density 0.003%

    No Known Activations