© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239046
    Prev
    Next
    INDEX
    Explanations

    data items separated by commas

    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_25_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
    </strong>
    0.43
     Im
    0.42
     Tra
    0.39
     NE
    0.38
     Shir
    0.38
     ‍
    0.38
     Find
    0.37
     giàu
    0.37
     ‘
    0.37
     Aut
    0.37
    POSITIVE LOGITS
    镗
    0.44
     incumpl
    0.41
    ნენ
    0.40
     ಅವರಿಗೆ
    0.39
     அவருக்கு
    0.39
     sucedido
    0.39
     swamps
    0.39
    estellt
    0.38
    ৈধ
    0.38
    yai
    0.38
    Activations Density 0.017%

    No Known Activations