© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    solving mysteries

    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
    ক্ষণিক
    0.36
    ляти
    0.36
     চৈত
    0.35
    XT
    0.31
    Stories
    0.31
    
    0.31
    September
    0.31
     जस्टिस
    0.31
    Sin
    0.31
    Ά
    0.31
    POSITIVE LOGITS
     unlock
    1.39
     unlocking
    1.34
     unlocked
    1.30
     unlocks
    1.27
    unlock
    1.23
     Unlock
    1.18
     unravel
    1.17
    Unlock
    1.11
    解
    1.11
     decode
    1.06
    Activations Density 0.260%

    No Known Activations