© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78193
    Prev
    Next
    INDEX
    Explanations

    various complex multifaceted

    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_31_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
     दो
    0.36
     ಎರಡು
    0.32
     두
    0.32
     दोन
    0.31
     две
    0.31
     দুটো
    0.30
     zwei
    0.30
    Councillor
    0.29
     deux
    0.29
    獲
    0.29
    POSITIVE LOGITS
     allerlei
    0.46
    いろいろ
    0.32
    复杂的
    0.32
     sämt
    0.32
    浑
    0.32
     multifaceted
    0.31
     комплекс
    0.31
    复杂
    0.31
     entire
    0.31
     everything
    0.30
    Activations Density 0.064%

    No Known Activations