© 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. 218273
    Prev
    Next
    INDEX
    Explanations

    hidden Features, opportunity, Room, gems, collection, History, relationships, motivations, prophecy

    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
     befinden
    0.39
    narrow
    0.39
    眇
    0.38
    ilitar
    0.37
     Modelling
    0.36
    Wasser
    0.36
    <0xB1>
    0.36
    ívar
    0.35
     befindet
    0.35
    rainer
    0.35
    POSITIVE LOGITS
     চাহিদা
    0.47
     poison
    0.40
     માંગ
    0.39
     চাহি
    0.38
     मागणी
    0.38
    φε
    0.37
     aisles
    0.37
     ആവശ്യ
    0.37
    繼
    0.36
     zaht
    0.36
    Activations Density 0.004%

    No Known Activations