© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14253
    Prev
    Next
    INDEX
    Explanations

    official node images and variants

    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_40_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
    setosa
    0.43
     FILL
    0.42
     按
    0.39
     Allocate
    0.38
    服務
    0.38
     SSO
    0.37
     உட்க
    0.37
     frust
    0.37
    LEFT
    0.37
     給
    0.36
    POSITIVE LOGITS
    官方
    0.49
     official
    0.48
     आधिकारिक
    0.46
     resmi
    0.45
     officielle
    0.44
     officially
    0.43
    Official
    0.43
     OFFICIAL
    0.41
     Official
    0.40
     offizi
    0.39
    Activations Density 0.009%

    No Known Activations