© 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. 15900
    Prev
    Next
    INDEX
    Explanations

    rare cases of

    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
     Shil
    0.40
     unilaterally
    0.39
    _*
    0.37
     centrally
    0.36
     **
    0.35
     escalating
    0.35
     autonomously
    0.34
     abruptly
    0.34
    蜀
    0.34
     provoked
    0.33
    POSITIVE LOGITS
     rare
    2.14
     Rare
    2.00
    Rare
    1.90
    rare
    1.77
     rares
    1.68
     दुर्लभ
    1.57
     rarer
    1.55
     rarity
    1.52
     raro
    1.52
     rara
    1.45
    Activations Density 0.023%

    No Known Activations