© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216826
    Prev
    Next
    INDEX
    Explanations

    If then reasoning

    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_47_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
    Bever
    0.45
    示
    0.37
     Beverly
    0.36
    wedd
    0.36
     Emery
    0.35
     Bever
    0.35
     উৎসাহ
    0.35
    uti
    0.33
     évo
    0.33
    porcion
    0.33
    POSITIVE LOGITS
    ពិស
    0.47
     clickable
    0.37
     queryset
    0.37
     fuzz
    0.37
    瑯
    0.36
     net
    0.36
     LPS
    0.36
     起
    0.36
     الخمسه
    0.36
     newline
    0.35
    Activations Density 0.000%

    No Known Activations