© 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. 218301
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    ppings
    0.20
    perform
    0.19
     পরিপ্রে
    0.19
    术
    0.18
     رکھتی
    0.18
     بچہ
    0.18
    pping
    0.18
    صیٰ
    0.17
    ন্নত
    0.17
     ඒවා
    0.17
    POSITIVE LOGITS
     indicar
    0.20
     lewat
    0.19
    那位
    0.19
     această
    0.19
     abhid
    0.18
     эту
    0.18
     wreath
    0.18
     biomed
    0.18
     i
    0.18
     cette
    0.18
    Activations Density 0.010%

    No Known Activations