© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 118050
    Prev
    Next
    INDEX
    Explanations

    material, size, or composition

    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_27_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
     colaborar
    0.37
     poca
    0.35
     बता
    0.34
     Prov
    0.33
    வே
    0.33
    Cer
    0.33
    澎
    0.33
     collaboration
    0.33
     collaborations
    0.33
    Serv
    0.32
    POSITIVE LOGITS
    ดย
    0.43
     stencil
    0.43
    摡
    0.40
     utu
    0.39
    bruck
    0.39
    stencil
    0.38
    คอม
    0.38
    ڈنگ
    0.37
     flutter
    0.37
    owały
    0.37
    Activations Density 0.013%

    No Known Activations