© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90288
    Prev
    Next
    INDEX
    Explanations

    beginners vs experienced

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     нее
    0.45
    бат
    0.42
    。“
    0.42
    氅
    0.41
     플
    0.41
     หา
    0.40
    ব্যা
    0.40
    集
    0.39
     мет
    0.39
     Dung
    0.39
    POSITIVE LOGITS
    ive
    0.42
     RC
    0.41
    ortium
    0.41
     Reaction
    0.39
    enta
    0.39
    পন্ন
    0.39
    ifty
    0.38
    jalanan
    0.38
    राधिक
    0.38
    stimulated
    0.38
    Activations Density 0.001%

    No Known Activations