© 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
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136854
    Prev
    Next
    INDEX
    Explanations

    wiktionary

    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_37_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
     ँ
    0.42
    Women
    0.38
    émor
    0.37
    angleright
    0.37
    投标人
    0.37
    壑
    0.37
    newMark
    0.36
    نساء
    0.36
    蹉
    0.36
    irán
    0.36
    POSITIVE LOGITS
    MS
    0.38
     ping
    0.37
     renvers
    0.37
     пода
    0.37
    賚
    0.37
     effic
    0.37
     ramb
    0.35
    JS
    0.35
     Rami
    0.35
     encycl
    0.35
    Activations Density 0.001%

    No Known Activations