© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4128
    Prev
    Next
    INDEX
    Explanations

    prisms and refraction

    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_40_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
    Molecular
    0.39
     rubs
    0.35
    ሷ
    0.35
    ヅ
    0.35
     Molecular
    0.34
    Immutable
    0.34
     Pads
    0.34
    
    0.33
    ^{*},
    0.33
    倦
    0.33
    POSITIVE LOGITS
     prism
    1.54
     prisms
    1.43
     Prism
    1.32
    prism
    1.32
     prisma
    1.23
     प्रिज्म
    1.10
    prisma
    1.06
     Prisma
    1.02
    棱
    0.99
     prismatic
    0.92
    Activations Density 0.059%

    No Known Activations