© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79848
    Prev
    Next
    INDEX
    Explanations

    phrases separated by commas

    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
    Not in Any Lists

    No Comments

    Negative Logits
    첨
    0.33
     hic
    0.32
     cela
    0.31
    }}^{*
    0.31
     ليس
    0.31
     좌
    0.31
    Ctrl
    0.29
     huile
    0.29
    τητας
    0.29
     infinitely
    0.29
    POSITIVE LOGITS
    ።
    0.31
    bsite
    0.30
     อุ
    0.30
          
    0.30
     DR
    0.30
    entrée
    0.29
    nar
    0.29
    DR
    0.29
     nhánh
    0.29
     Uranium
    0.29
    Activations Density 0.027%

    No Known Activations