© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35976
    Prev
    Next
    INDEX
    Explanations

    A

    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_50_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
     पूर्वा
    0.40
     chu
    0.40
     Yarn
    0.38
     EA
    0.38
    рт
    0.37
    érm
    0.37
    俞
    0.37
    শা
    0.37
     रॉ
    0.37
     zhu
    0.37
    POSITIVE LOGITS
    Bris
    0.45
    pone
    0.42
     وده
    0.39
    FFF
    0.36
    الحكم
    0.36
    airy
    0.36
    one
    0.35
    ONE
    0.35
    bris
    0.34
    Women
    0.34
    Activations Density 0.001%

    No Known Activations