© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16778
    Prev
    Next
    INDEX
    Explanations

    前明

    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_15_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
     piss
    0.32
     '
    0.28
     february
    0.28
     tus
    0.27
     perverse
    0.27
    ”
    0.26
     divorce
    0.26
    ியான
    0.26
     wasteful
    0.26
     berkom
    0.26
    POSITIVE LOGITS
     தினத்த
    0.36
     चिल्ड्रन
    0.35
     አበባ
    0.33
    Schmidt
    0.33
     Nokia
    0.33
    кі
    0.32
     Batteries
    0.31
     Kodak
    0.31
    
    0.31
     ګرځنده
    0.30
    Activations Density 0.086%

    No Known Activations