© 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. 213653
    Prev
    Next
    INDEX
    Explanations

    Purpose

    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
     manifolds
    0.41
    飜
    0.41
    િન
    0.39
     Dan
    0.39
     Research
    0.38
    dan
    0.38
    лин
    0.38
     (&
    0.38
     Ext
    0.37
     Materials
    0.37
    POSITIVE LOGITS
    ชุม
    0.39
    社区
    0.39
     ግራም
    0.37
    idot
    0.36
     antig
    0.36
    etra
    0.35
     tir
    0.35
    community
    0.35
    社區
    0.35
     ভো
    0.34
    Activations Density 0.005%

    No Known Activations