© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217699
    Prev
    Next
    INDEX
    Explanations

    train station line

    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_16_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
     نمای
    0.22
    কুমার
    0.21
     aujourd
    0.21
    Graph
    0.21
     langsung
    0.20
    '}
    0.20
    írez
    0.20
    tao
    0.20
    Po
    0.20
     expressions
    0.20
    POSITIVE LOGITS
    ﻪ
    0.24
     курса
    0.24
    啤酒
    0.24
     فلسطين
    0.23
     Функция
    0.22
     Сере
    0.22
     население
    0.21
     Эк
    0.21
     ਵਿਚ
    0.21
     canary
    0.21
    Activations Density 0.001%

    No Known Activations