© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196844
    Prev
    Next
    INDEX
    Explanations

    AP and IB exams

    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_27_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
    olved
    0.45
     corret
    0.42
     successivo
    0.40
     competed
    0.40
     Calcd
    0.40
    ajikan
    0.39
    哗
    0.39
     مکمل
    0.38
    ToArabic
    0.38
    的市场
    0.38
    POSITIVE LOGITS
     помочь
    0.40
     crucial
    0.39
     hefty
    0.38
     vitally
    0.38
     Запа
    0.38
    »
    0.38
     ayudará
    0.37
    helping
    0.37
    ︎
    0.37
    friction
    0.36
    Activations Density 0.000%

    No Known Activations