© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76928
    Prev
    Next
    INDEX
    Explanations

    one last

    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_53_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
    نسب
    0.38
    պես
    0.37
     रद्द
    0.36
    ὀ
    0.34
    പ്പോള്‍
    0.33
    ],$
    0.33
     estoy
    0.33
    Fortunately
    0.33
     Fortunately
    0.33
     estás
    0.32
    POSITIVE LOGITS
    Tru
    0.36
    XE
    0.35
    𓃵
    0.34
     ­
    0.34
     ?-
    0.34
     Hakone
    0.34
    ರ್‌
    0.33
     ®
    0.33
    िका
    0.33
    V
    0.33
    Activations Density 0.005%

    No Known Activations