© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99930
    Prev
    Next
    INDEX
    Explanations

    magic kingdom or controller

    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_14_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
    Գ
    0.53
     minimising
    0.53
     prevention
    0.52
    ین
    0.52
    ก
    0.51
     centralised
    0.50
    ブ
    0.50
     ampia
    0.49
     protezione
    0.48
     completa
    0.48
    POSITIVE LOGITS
    playSound
    0.55
    смотрим
    0.55
     ইহ
    0.54
    getContext
    0.54
     έχουν
    0.53
     jóvenes
    0.53
     হুই
    0.52
     택
    0.52
     සමා
    0.52
    ){
    0.52
    Activations Density 0.000%

    No Known Activations