© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212930
    Prev
    Next
    INDEX
    Explanations

    rear

    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_50_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
     end
    0.87
    端
    0.68
    End
    0.64
     End
    0.64
    end
    0.64
     конец
    0.59
    端的
    0.56
     نهايه
    0.55
     نهاية
    0.55
    END
    0.54
    POSITIVE LOGITS
     महत्
    0.37
    閇
    0.36
    Cork
    0.36
    捪
    0.36
     hiper
    0.35
    etails
    0.35
    广东省
    0.35
    Bj
    0.35
     योज
    0.35
    BackendAuth
    0.33
    Activations Density 0.001%

    No Known Activations