© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74513
    Prev
    Next
    INDEX
    Explanations

    those SP components

    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_31_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
    箖
    0.43
     Guarant
    0.40
    googleapis
    0.39
    Buffer
    0.38
    料理
    0.38
    findElements
    0.37
    棍
    0.37
     мяг
    0.37
     الحسن
    0.37
     Ria
    0.36
    POSITIVE LOGITS
    앱
    0.45
     app
    0.38
     smartphone
    0.38
     scintill
    0.37
     parallax
    0.37
     swan
    0.36
    ivan
    0.36
     AppModule
    0.35
    olini
    0.34
    oter
    0.34
    Activations Density 0.000%

    No Known Activations