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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6159
    Prev
    Next
    INDEX
    Explanations

    entertainment, memorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    Manual
    0.39
     manual
    0.39
     Manual
    0.37
     manualmente
    0.34
    穀
    0.33
    manual
    0.32
     MANUAL
    0.32
     मैनु
    0.32
     manu
    0.31
     manuel
    0.31
    POSITIVE LOGITS
     entretenimiento
    0.48
     entertainment
    0.46
     Entertainment
    0.45
    Entertainment
    0.45
    entertainment
    0.44
     entertain
    0.39
    娱乐
    0.36
    娛
    0.32
    蒐
    0.32
    娛樂
    0.31
    Activations Density 0.009%

    No Known Activations