© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127663
    Prev
    Next
    INDEX
    Explanations

    numbers and measurement units

    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_37_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
    笔者
    0.38
    sky
    0.37
    pmod
    0.37
    NHS
    0.36
    માન
    0.36
     medicamentos
    0.36
    を入力
    0.36
    檚
    0.36
    unpack
    0.35
    ROLLER
    0.35
    POSITIVE LOGITS
     Middle
    0.42
     Alexandria
    0.41
     сре
    0.39
    戛
    0.39
     DEVICE
    0.38
     authorised
    0.38
     Сере
    0.37
     personalisation
    0.37
     উজ
    0.37
     assembly
    0.36
    Activations Density 0.000%

    No Known Activations