© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77090
    Prev
    Next
    INDEX
    Explanations

    enforce consistent documentation and reporting

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🐚
    0.36
    Ore
    0.35
    ehle
    0.35
    vert
    0.34
    睃
    0.34
     pl
    0.33
     dechlorination
    0.33
    佇
    0.33
    हल
    0.33
    ieson
    0.33
    POSITIVE LOGITS
     Enforcement
    0.50
     enforcement
    0.48
     consistently
    0.45
     enforce
    0.44
    Correct
    0.43
    正確
    0.41
     Correct
    0.41
     enforcing
    0.41
     mandatory
    0.41
    习惯
    0.41
    Activations Density 0.074%

    No Known Activations