© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168139
    Prev
    Next
    INDEX
    Explanations

    "I" or "we" followed by speech or thought ("meant", "just", "It", "all", "how", "that")

    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_31_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
     predict
    0.36
     సంబంధించిన
    0.36
     있었
    0.35
    嶄
    0.35
     ट्व
    0.35
    ropy
    0.34
     tempted
    0.33
     दरवा
    0.33
     yearn
    0.33
     Princip
    0.33
    POSITIVE LOGITS
    遁
    0.38
    dzić
    0.37
    Repeat
    0.37
    域名
    0.37
    ្ខ
    0.37
    таль
    0.36
     jasno
    0.36
     уго
    0.36
    せず
    0.35
     ánimo
    0.35
    Activations Density 0.011%

    No Known Activations