© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78240
    Prev
    Next
    INDEX
    Explanations

    magic, spells, summoning, rituals

    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
    ৭০
    0.38
    稳
    0.38
     industrielle
    0.37
     compon
    0.37
    工业
    0.37
    是可以
    0.37
     geese
    0.36
    Chrome
    0.36
    ADMIN
    0.36
     ಸಂಪ
    0.36
    POSITIVE LOGITS
     observ
    0.39
     Reels
    0.38
     implant
    0.37
     imagination
    0.37
    饮食
    0.36
     imaginations
    0.36
    ̤
    0.35
     Markdown
    0.35
     observación
    0.35
     Fluid
    0.35
    Activations Density 0.002%

    No Known Activations