© 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. 36980
    Prev
    Next
    INDEX
    Explanations

    od

    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
     البيان
    0.38
    tikz
    0.37
     اﻷ
    0.36
     مهمه
    0.36
     ఓ
    0.36
     அதிகமான
    0.36
    ᅪ
    0.35
     الارد
    0.35
    侓
    0.35
    वित
    0.35
    POSITIVE LOGITS
    den
    0.49
     din
    0.48
     Marco
    0.48
    kin
    0.46
    din
    0.45
    Din
    0.45
    Marco
    0.44
    ジン
    0.43
    imd
    0.43
     den
    0.42
    Activations Density 0.001%

    No Known Activations