© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34407
    Prev
    Next
    INDEX
    Explanations

    chemistry and substances

    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
    끽
    0.41
    CCIÓN
    0.39
     Cách
    0.39
    čních
    0.39
    мір
    0.38
    
    0.38
     hòa
    0.38
     북
    0.38
    금
    0.38
    굉
    0.37
    POSITIVE LOGITS
     dire
    0.41
     kern
    0.40
     pitch
    0.37
    ازی
    0.37
     kiri
    0.37
     actinides
    0.37
     blues
    0.37
     pizza
    0.37
     xanth
    0.37
     inter
    0.36
    Activations Density 0.001%

    No Known Activations