© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4231
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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_39_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
     सियासी
    0.44
    激素
    0.43
    ocese
    0.42
    诰
    0.40
     atmospheric
    0.40
    DrawerToggle
    0.40
     ሂደት
    0.39
     análisis
    0.39
    োদ্ধ
    0.39
    应对
    0.38
    POSITIVE LOGITS
     india
    0.45
     Delhi
    0.45
     India
    0.43
     भारत
    0.41
    India
    0.41
     delhi
    0.41
    Delhi
    0.41
     भारता
    0.40
    ^{\#
    0.40
    熱
    0.40
    Activations Density 0.004%

    No Known Activations