© 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. 57700
    Prev
    Next
    INDEX
    Explanations

    present participle suffix

    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
    Negative Logits
    as
    1.03
    的
    0.99
    的目标
    0.84
    лия
    0.80
    的和
    0.79
    kirche
    0.79
    an
    0.78
    wicklung
    0.77
    ‌ها
    0.76
    的回
    0.76
    POSITIVE LOGITS
    म
    1.43
    ב
    1.38
    ک
    1.38
    મ
    1.34
    2
    1.30
    دی
    1.27
    می
    1.21
    ტ
    1.21
    ম
    1.18
    미
    1.18
    Activations Density 0.000%

    No Known Activations