© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51089
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_31_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
     politely
    0.41
     bare
    0.39
    差異
    0.39
    
    0.39
     ebook
    0.36
     प्रकरण
    0.36
    하면
    0.36
    proper
    0.35
    versch
    0.35
    penas
    0.35
    POSITIVE LOGITS
     fragments
    0.39
    侬
    0.38
     Encryption
    0.38
     Pilot
    0.37
    edor
    0.36
    片段
    0.36
    奎
    0.36
    炤
    0.35
     ইঙ্গিত
    0.35
     Kasım
    0.35
    Activations Density 0.014%

    No Known Activations