© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140244
    Prev
    Next
    INDEX
    Explanations

    parse numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ตุ
    0.42
    慥
    0.41
     生成
    0.41
     America
    0.39
     constructs
    0.39
    峼
    0.38
    生成
    0.38
    비스
    0.38
     ग्लो
    0.38
     generating
    0.38
    POSITIVE LOGITS
     ISO
    0.45
     iso
    0.43
     Viewed
    0.40
     изо
    0.40
     Iso
    0.40
    рё
    0.39
    iso
    0.38
    ISO
    0.37
    isf
    0.37
     proport
    0.37
    Activations Density 0.002%

    No Known Activations