© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219753
    Prev
    Next
    INDEX
    Explanations

    wild

    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_47_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
    igated
    0.39
    stats
    0.37
    감
    0.36
    กำ
    0.36
    examined
    0.35
     सत्
    0.35
     attested
    0.35
     atacar
    0.35
    ALLOWED
    0.34
    thi
    0.34
    POSITIVE LOGITS
    issão
    0.42
     بع
    0.40
     Nis
    0.40
     taşı
    0.39
     Louisa
    0.39
    NIS
    0.39
    紹
    0.39
     poisonous
    0.38
     ASP
    0.38
    RAN
    0.38
    Activations Density 0.000%

    No Known Activations