© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208842
    Prev
    Next
    INDEX
    Explanations

    websites, methods, constitution

    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_20_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
     spinal
    0.52
    spinal
    0.50
    ı
    0.49
    ysts
    0.46
     روی
    0.45
     क्रमशः
    0.44
     theory
    0.44
    duction
    0.44
     वाह
    0.44
     sering
    0.44
    POSITIVE LOGITS
     besonderen
    0.52
    효
    0.52
    Влади
    0.49
    」（
    0.49
     还
    0.47
    그러
    0.47
    Lambert
    0.47
    蓝牙
    0.46
    마트
    0.46
    ”（
    0.46
    Activations Density 0.000%

    No Known Activations