© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16250
    Prev
    Next
    INDEX
    Explanations

    overview, guide, introduction

    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_15_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
    Could
    0.39
    Lag
    0.36
     whose
    0.35
     lagoon
    0.34
    et
    0.34
    ையை
    0.33
    溜
    0.33
     amely
    0.33
     Quantity
    0.32
    姮
    0.32
    POSITIVE LOGITS
     तुलना
    0.41
     ከተ
    0.37
    zechoslovak
    0.35
     នៅ
    0.34
     koncept
    0.34
     निर्धारण
    0.33
    Ơ
    0.32
     אותו
    0.32
     Barth
    0.32
    فتح
    0.32
    Activations Density 0.121%

    No Known Activations