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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6065
    Prev
    Next
    INDEX
    Explanations

    permanent industry labels

    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_40_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
    保湿
    0.39
    予防
    0.38
    保养
    0.38
    薊
    0.37
    淋
    0.36
     bract
    0.35
    jacking
    0.35
    ß
    0.35
    ixer
    0.34
     کاروبار
    0.34
    POSITIVE LOGITS
     Trag
    0.39
     Permanent
    0.38
    μεσα
    0.38
     permanent
    0.38
     Perman
    0.38
     permanente
    0.37
     स्थायी
    0.37
     reconhecimento
    0.36
     Observe
    0.36
     Moderne
    0.36
    Activations Density 0.000%

    No Known Activations