© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78696
    Prev
    Next
    INDEX
    Explanations

    lad

    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_53_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
     Leb
    0.46
    〽
    0.39
     레
    0.38
     الوق
    0.38
    ্রান্ত
    0.37
    ])[
    0.37
    )&&
    0.37
    挚
    0.36
     مو
    0.36
     Yuki
    0.36
    POSITIVE LOGITS
    lad
    1.15
    Lad
    1.05
     lad
    1.02
    лады
    1.02
    лад
    0.97
    lade
    0.95
    ład
    0.94
    lád
    0.93
     Lad
    0.93
    лада
    0.90
    Activations Density 0.007%

    No Known Activations