© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15698
    Prev
    Next
    INDEX
    Explanations

    tablet, crystal, or colored objects

    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_34_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
     saves
    0.41
     Schedules
    0.38
    添
    0.38
     protein
    0.37
     spectra
    0.37
     treatment
    0.36
     compounds
    0.35
    ၽ
    0.35
    年
    0.35
     Buddha
    0.34
    POSITIVE LOGITS
     tablets
    0.48
     Tablets
    0.47
     цвет
    0.46
     красивые
    0.43
     табле
    0.43
    idescent
    0.42
    Tablet
    0.41
    icolored
    0.40
     crystals
    0.38
     Численность
    0.38
    Activations Density 0.033%

    No Known Activations