© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7560
    Prev
    Next
    INDEX
    Explanations

    Chinese names and titles

    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_39_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
    elementProp
    0.42
    女士
    0.42
    Cindy
    0.40
    INFINITY
    0.40
     complejos
    0.39
    Penny
    0.37
    ινων
    0.37
    ዊ
    0.37
    넵
    0.36
     complejidad
    0.36
    POSITIVE LOGITS
     tiger
    0.39
     village
    0.37
     nin
    0.36
     envoy
    0.35
     Reporting
    0.34
     clan
    0.34
     disciple
    0.34
     tigers
    0.34
     bandit
    0.34
     master
    0.34
    Activations Density 0.009%

    No Known Activations