© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33495
    Prev
    Next
    INDEX
    Explanations

    get; set;

    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_40_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
     อี
    0.38
    ಊ
    0.36
    𝗌
    0.36
     এলিট
    0.34
    лому
    0.33
     Beur
    0.33
    Вакансия
    0.33
     Altogether
    0.32
     अफवाह
    0.32
    Ռ
    0.32
    POSITIVE LOGITS
    get
    0.36
     Gets
    0.35
     Get
    0.35
     patina
    0.35
     नम
    0.34
    aria
    0.33
    NAM
    0.33
    南北
    0.33
     get
    0.32
    Get
    0.32
    Activations Density 0.001%

    No Known Activations