© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151873
    Prev
    Next
    INDEX
    Explanations

    been expecting or trained

    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
    Negative Logits
    FormData
    0.23
    硬盘
    0.23
    ESSION
    0.22
    WebKit
    0.22
     데이터
    0.20
    인
    0.20
    iren
    0.20
     posisi
    0.20
    PlainText
    0.20
    Ht
    0.20
    POSITIVE LOGITS
    ⚊
    0.21
     organizers
    0.20
     S
    0.19
     well
    0.19
     folks
    0.19
     truly
    0.19
     Cups
    0.19
     |”
    0.19
    الل
    0.18
     organisers
    0.18
    Activations Density 0.012%

    No Known Activations