© 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. 90217
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
     każde
    0.40
     Vẽ
    0.39
     anomalous
    0.39
     sorrows
    0.39
     muttered
    0.39
     ∈
    0.38
     ills
    0.37
    同学们
    0.37
     meaningless
    0.37
     UNNEEDED
    0.37
    POSITIVE LOGITS
    streetmap
    0.42
    һы
    0.38
    絭
    0.38
    ICKEL
    0.38
    лау
    0.37
    Leaving
    0.36
    تاء
    0.36
    Having
    0.35
     společ
    0.35
    сква
    0.35
    Activations Density 0.001%

    No Known Activations