© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171151
    Prev
    Next
    INDEX
    Explanations

    depersonalization

    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_56_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
     де
    2.53
     De
    2.41
    De
    2.34
     DE
    2.28
     de
    2.25
     Де
    2.19
    デ
    2.16
    de
    2.14
    德
    2.09
     दे
    2.03
    POSITIVE LOGITS
    ডাক
    0.36
    ាត់
    0.35
    яд
    0.34
     दल
    0.33
    桫
    0.33
    ⵚ
    0.33
     %=
    0.33
    urrence
    0.33
    omena
    0.33
    sdag
    0.33
    Activations Density 0.003%

    No Known Activations