© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202238
    Prev
    Next
    INDEX
    Explanations

    Filipino particles/markers

    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
    球面
    0.43
    clam
    0.42
     schon
    0.39
     Уже
    0.38
    すでに
    0.37
    `],
    0.37
    γή
    0.37
    ُو
    0.37
     juba
    0.37
    ̃
    0.36
    POSITIVE LOGITS
    డిగా
    0.40
    소스
    0.39
     ваша
    0.38
     IAU
    0.37
     вашей
    0.37
     biotin
    0.37
     cigarette
    0.36
     ስለዚህ
    0.36
    iniz
    0.35
    笾
    0.35
    Activations Density 0.000%

    No Known Activations