© 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. 130425
    Prev
    Next
    INDEX
    Explanations

    History and Art

    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
     ال
    0.41
     setLayout
    0.40
     WSA
    0.40
     암
    0.39
    िज्म
    0.39
     ईशान
    0.37
     ankle
    0.37
     Descent
    0.37
    悚
    0.37
     layout
    0.36
    POSITIVE LOGITS
    KON
    0.40
    тельно
    0.38
    सम्म
    0.37
    KBr
    0.37
    DataLoader
    0.36
    Params
    0.35
     coup
    0.35
     ঘোষণ
    0.35
     Gard
    0.35
    占
    0.35
    Activations Density 0.006%

    No Known Activations