© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55096
    Prev
    Next
    INDEX
    Explanations

    E or ear

    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_55_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
     earns
    0.48
     earned
    0.46
     tien
    0.44
    earned
    0.43
     kiếm
    0.40
    稼
    0.39
    sein
    0.38
     earning
    0.38
    獲得
    0.38
    tien
    0.36
    POSITIVE LOGITS
     E
    2.92
    E
    2.05
     ई
    1.55
    ear
    1.43
     Е
    1.39
    𝐸
    1.31
    Ｅ
    1.30
     ear
    1.21
     Ear
    1.13
     e
    1.10
    Activations Density 0.010%

    No Known Activations