© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177438
    Prev
    Next
    INDEX
    Explanations

    venues and places

    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
    鄭
    0.47
     Newcastle
    0.43
     Newark
    0.43
     Bonner
    0.43
     Buen
    0.43
    郑
    0.43
     ट
    0.42
     Newton
    0.42
     Lacey
    0.41
     бол
    0.41
    POSITIVE LOGITS
     KIA
    0.39
    শ্য
    0.38
    Stadium
    0.37
    鬘
    0.36
     MCSF
    0.35
    Glor
    0.35
     Hallo
    0.35
     خانو
    0.35
    ルス
    0.35
    ILO
    0.35
    Activations Density 0.003%

    No Known Activations