© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35673
    Prev
    Next
    INDEX
    Explanations

    WW

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ux
    0.41
     Wei
    0.41
     câ
    0.40
     Mei
    0.39
     Bris
    0.38
     الع
    0.38
    wei
    0.38
    ⓑ
    0.38
     Wyoming
    0.37
     Leh
    0.37
    POSITIVE LOGITS
    ti
    0.40
    acz
    0.39
    yti
    0.38
     নিষ্পত্তি
    0.38
    licken
    0.37
    তখন
    0.37
    駄
    0.36
    het
    0.36
    FT
    0.36
    ティー
    0.36
    Activations Density 0.000%

    No Known Activations