© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235883
    Prev
    Next
    INDEX
    Explanations

    alleged, argued, suggests, state

    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_32_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
    のだろう
    0.40
    在這個
    0.36
    堝
    0.36
    പ്പിച്ചി
    0.35
    Ⲇ
    0.35
    ãs
    0.35
    ਮ
    0.35
     गुजराती
    0.35
    ︵
    0.35
    鲢
    0.35
    POSITIVE LOGITS
     Tras
    0.42
    ydi
    0.41
     During
    0.38
    fortun
    0.38
     результатом
    0.38
     resultados
    0.38
     fundación
    0.38
     tast
    0.37
     Thos
    0.37
     Mr
    0.37
    Activations Density 0.001%

    No Known Activations