© 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. 35978
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    蕤
    0.38
    odz
    0.38
    Summit
    0.38
     Magdalena
    0.37
    冊
    0.37
     Mo
    0.36
    endosi
    0.35
    CodeGen
    0.35
    pageNum
    0.35
    册
    0.35
    POSITIVE LOGITS
     keperluan
    0.40
     गरजे
    0.39
     swit
    0.39
    Michael
    0.39
     Jaime
    0.38
    दम
    0.38
    仵
    0.38
     Michael
    0.38
     맞춰
    0.38
     jam
    0.37
    Activations Density 0.001%

    No Known Activations