© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212014
    Prev
    Next
    INDEX
    Explanations

    sperm, gametes, fertilization

    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_20_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
    讲述
    0.46
     탐
    0.46
    IVED
    0.40
    ULA
    0.39
    Entropy
    0.39
    expandindo
    0.38
    VENT
    0.38
     श्रीवास्तव
    0.37
    dilate
    0.37
    Rome
    0.37
    POSITIVE LOGITS
    cur
    0.50
     Im
    0.49
     minyak
    0.48
     ž
    0.45
     टेक्
    0.44
     डूब
    0.44
     pprint
    0.43
     oil
    0.42
     vak
    0.42
    aj
    0.42
    Activations Density 0.001%

    No Known Activations