© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257339
    Prev
    Next
    INDEX
    Explanations

    loss of identity

    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_22_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
    𒆳
    0.38
    概率
    0.36
     chick
    0.36
     phạt
    0.36
     আহম
    0.35
    城県
    0.35
     Greene
    0.35
    lington
    0.34
    ظ
    0.34
    ﻡ
    0.34
    POSITIVE LOGITS
     subsequently
    0.40
    ிற்ப
    0.39
     afterward
    0.38
    original
    0.38
    ቆዳ
    0.38
     콜
    0.37
    consult
    0.37
     reaff
    0.37
    ต้น
    0.37
     origin
    0.36
    Activations Density 0.006%

    No Known Activations