© 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. 212799
    Prev
    Next
    INDEX
    Explanations

    AI model performance

    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
    amen
    0.38
    бто
    0.37
    Cardinal
    0.36
    ỡng
    0.35
    ฑ
    0.35
     Josie
    0.35
    吊
    0.35
     मंद
    0.34
    Amenities
    0.34
    rishna
    0.34
    POSITIVE LOGITS
    ittee
    0.41
    খার
    0.39
     largeur
    0.38
    esser
    0.38
    fir
    0.38
    柰
    0.38
    يرات
    0.37
    ewater
    0.37
    ire
    0.37
     Shaun
    0.37
    Activations Density 0.000%

    No Known Activations