© 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. 195764
    Prev
    Next
    INDEX
    Explanations

    Mittens

    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
     FAIR
    0.49
    ILI
    0.43
     Fairfax
    0.41
    აში
    0.41
    ixos
    0.40
    ili
    0.39
    諷
    0.38
    ROS
    0.38
    和服务
    0.37
     fake
    0.37
    POSITIVE LOGITS
    中華
    0.45
    ێ
    0.43
    mipmap
    0.40
    中华
    0.38
    Ԁ
    0.38
    भा
    0.36
     গ্রন্থ
    0.36
    ண
    0.36
    iot
    0.36
    াধীন
    0.36
    Activations Density 0.001%

    No Known Activations