© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30597
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation mixed with 'CREATE'

    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_40_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
    uzie
    0.40
     محر
    0.39
    uzzi
    0.38
     মাদক
    0.37
    亢
    0.36
    idc
    0.36
     AUG
    0.36
    Jn
    0.35
    ouest
    0.35
    Ouest
    0.34
    POSITIVE LOGITS
     ग्रेजु
    0.38
     Forced
    0.38
    涌
    0.37
     syst
    0.36
     chiral
    0.36
     Agar
    0.36
     Gastro
    0.35
    চৈতন্য
    0.35
    хозяй
    0.35
     sys
    0.34
    Activations Density 0.013%

    No Known Activations