© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 148566
    Prev
    Next
    INDEX
    Explanations

    insurance contributions by income or work

    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_18_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
    وراق
    0.30
    طبيق
    0.27
     নারায়ণ
    0.27
    garakan
    0.26
    沓
    0.26
     März
    0.26
    ﺩ
    0.25
    纍
    0.25
     bệnh
    0.25
     beneficios
    0.25
    POSITIVE LOGITS
    BO
    0.29
     BO
    0.28
    éb
    0.27
    ometry
    0.25
    BP
    0.25
     Product
    0.24
    යු
    0.24
     транспорта
    0.24
     Intelligence
    0.24
     interrupt
    0.23
    Activations Density 0.001%

    No Known Activations