© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121605
    Prev
    Next
    INDEX
    Explanations

    But

    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
    Negative Logits
    及ひ
    0.46
     proviene
    0.39
     arose
    0.39
    下一个
    0.38
     डिप
    0.38
     неско
    0.38
     IMPORTANT
    0.37
     keinen
    0.37
     african
    0.37
    髋
    0.37
    POSITIVE LOGITS
    icycl
    0.46
     طے
    0.41
     appealing
    0.41
     PTO
    0.39
     podľa
    0.38
     Rund
    0.37
     Schu
    0.37
     Mala
    0.37
     living
    0.36
     Ora
    0.36
    Activations Density 0.002%

    No Known Activations