© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6133
    Prev
    Next
    INDEX
    Explanations

    microsoft, Xbox, Copilot

    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
    ቼ
    0.41
     evaluations
    0.41
     UW
    0.40
     legitimate
    0.39
     PCI
    0.39
     legitimately
    0.38
     depositions
    0.38
    Region
    0.37
    ემის
    0.37
     DBI
    0.37
    POSITIVE LOGITS
    ડે
    0.41
     Sury
    0.41
    érc
    0.40
    werke
    0.37
    ழு
    0.36
    뻤
    0.36
     забо
    0.35
     Chrome
    0.35
     разме
    0.35
     ডিম
    0.35
    Activations Density 0.015%

    No Known Activations