© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162532
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and specific names

    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_2_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
    3
    1.09
    ER
    1.06
    ↵↵
    1.04
     поведение
    0.94
    -
    0.94
    5
    0.94
    ر
    0.94
    روس
    0.93
    ة
    0.93
    ﺪ
    0.93
    POSITIVE LOGITS
     in
    1.08
     ONG
    1.08
    ב
    1.08
    א
    1.07
    ک
    1.02
    도
    1.01
    ও
    0.96
    س
    0.94
     IAAF
    0.94
     NYC
    0.92
    Activations Density 0.000%

    No Known Activations