© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200948
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    libraries
    0.40
     Electrical
    0.38
    localize
    0.38
    槸
    0.38
     wú
    0.37
    フィス
    0.35
     pageSize
    0.35
     താ
    0.34
     требо
    0.34
     yě
    0.34
    POSITIVE LOGITS
    的一部分
    0.44
    ([[
    0.42
     SAD
    0.41
    Rus
    0.40
     dialed
    0.39
     disreg
    0.38
     epitope
    0.37
     नावा
    0.37
    Oke
    0.37
    翹
    0.36
    Activations Density 0.004%

    No Known Activations