© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1417
    Prev
    Next
    INDEX
    Explanations

    new cloud technologies and services

    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
    აკ
    0.37
     group
    0.37
    插
    0.34
     grouping
    0.33
    اري
    0.33
    efficients
    0.33
     interchangeable
    0.33
    犮
    0.33
     Smart
    0.32
     ውጤ
    0.32
    POSITIVE LOGITS
     beurre
    0.38
     Tisch
    0.38
    Flagge
    0.37
     carbonate
    0.37
    carbonate
    0.37
     Casey
    0.36
     joht
    0.36
    Casey
    0.36
    돔
    0.36
    Server
    0.36
    Activations Density 0.008%

    No Known Activations