© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163613
    Prev
    Next
    INDEX
    Explanations

    start / before / first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    ိမ်
    0.55
    ုပ်
    0.54
    ﮏ
    0.52
     ಮಹಿ
    0.50
    ﺲ
    0.49
     Sénégal
    0.48
    唿
    0.47
    呼び
    0.47
    FAMILY
    0.46
    효
    0.46
    POSITIVE LOGITS
    பட்ட
    0.50
     сначала
    0.50
     பட்ட
    0.48
    事先
    0.46
     primero
    0.46
    nd
    0.45
     пробле
    0.45
     먼저
    0.44
    pand
    0.44
     سبق
    0.43
    Activations Density 0.000%

    No Known Activations