© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197844
    Prev
    Next
    INDEX
    Explanations

    Cre

    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_50_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
    inan
    0.41
    আর
    0.38
    adek
    0.38
    으니
    0.36
    職業
    0.36
    🐦
    0.36
     Πολ
    0.36
    계
    0.35
     profissionais
    0.35
     offrir
    0.35
    POSITIVE LOGITS
     آهنگ
    0.38
    ymb
    0.37
     wú
    0.37
    iostream
    0.36
    syllabus
    0.36
     Madame
    0.36
     besieged
    0.36
    mw
    0.35
     tafel
    0.35
    лизация
    0.35
    Activations Density 0.000%

    No Known Activations