© 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. 90477
    Prev
    Next
    INDEX
    Explanations

    graph structure components

    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
     Alignment
    0.46
    Alignment
    0.44
    हरी
    0.43
    潙
    0.40
     Align
    0.39
    靝
    0.38
    䧼
    0.37
    aligned
    0.37
    ゐ
    0.37
    なり
    0.36
    POSITIVE LOGITS
     variables
    0.45
     lorsqu
    0.42
     değişken
    0.41
     camas
    0.41
     bathrooms
    0.40
     bothers
    0.40
    Confidence
    0.39
     mocking
    0.39
     வண்ணம்
    0.39
     variable
    0.38
    Activations Density 0.003%

    No Known Activations