© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26823
    Prev
    Next
    INDEX
    Explanations

    discards or question

    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_10_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
    మాల
    0.51
     Oh
    0.50
     عد
    0.50
     ไข
    0.50
    وه
    0.49
     开
    0.48
     Kultur
    0.48
    óle
    0.47
     पाँच
    0.47
     Unle
    0.47
    POSITIVE LOGITS
     antennas
    0.55
     apertures
    0.55
    i
    0.55
     customers
    0.55
     guaranteeing
    0.55
     safeguarding
    0.54
    CIP
    0.54
     assuring
    0.52
    客様
    0.51
    Customers
    0.51
    Activations Density 0.000%

    No Known Activations