© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65531
    Prev
    Next
    INDEX
    Explanations

    lean

    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
    ăng
    0.43
     empowers
    0.41
     nost
    0.37
    chodzi
    0.37
    ವರು
    0.36
     उत्ते
    0.36
    ᄎ
    0.36
    研究生
    0.35
    掝
    0.35
     empowered
    0.35
    POSITIVE LOGITS
     lean
    1.71
     leaning
    1.66
     leaned
    1.62
     Lean
    1.52
    Lean
    1.45
     leans
    1.45
    lean
    1.39
    leaning
    1.33
     leaner
    1.07
    leans
    0.77
    Activations Density 0.220%

    No Known Activations