© 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. 30659
    Prev
    Next
    INDEX
    Explanations

    ArgumentNullException

    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
    divided
    0.45
    ingos
    0.43
    companies
    0.41
     divided
    0.41
     stopped
    0.39
    蟻
    0.39
    мп
    0.38
    stens
    0.38
     MaxPooling
    0.38
     harmful
    0.38
    POSITIVE LOGITS
     Capability
    0.39
     capace
    0.38
    꺼
    0.38
     ರಾಜ್ಯ
    0.37
     Ky
    0.36
    uur
    0.35
    ције
    0.35
    ्यूशन
    0.35
    ডা
    0.35
    ่วน
    0.34
    Activations Density 0.001%

    No Known Activations