© 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. 68612
    Prev
    Next
    INDEX
    Explanations

    JavaScript algorithms

    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
     confortável
    0.40
    榻
    0.39
     दिवस
    0.39
     Gruy
    0.39
    льм
    0.37
    வுகள்
    0.37
    বর্ধমান
    0.37
     Stow
    0.37
    悖
    0.37
    说是
    0.36
    POSITIVE LOGITS
     Advanced
    0.40
    apped
    0.38
     Accelerated
    0.37
     dura
    0.37
    ورت
    0.36
    Blitz
    0.36
    cery
    0.36
    ouser
    0.36
    icule
    0.36
     만들
    0.36
    Activations Density 0.001%

    No Known Activations