© 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. 16184
    Prev
    Next
    INDEX
    Explanations

    why does

    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
     they
    0.49
     তাঁরা
    0.46
    чными
    0.38
     Н
    0.37
     toolkit
    0.37
     loo
    0.37
     সেটা
    0.36
     اینکه
    0.36
     uintptr
    0.36
    燁
    0.36
    POSITIVE LOGITS
    ists
    0.43
     realities
    0.42
    istered
    0.42
     proponents
    0.42
     appointees
    0.42
     mediators
    0.41
     adherents
    0.41
     legislators
    0.41
     प्रोत्सा
    0.39
     পেয়েছে
    0.38
    Activations Density 0.019%

    No Known Activations