© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88930
    Prev
    Next
    INDEX
    Explanations

    wargame Red Dragon

    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_3_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
    en
    0.72
    pans
    0.70
    es
    0.68
    >-->
    0.67
    p
    0.63
    ก
    0.63
    il
    0.63
    ast
    0.61
    ard
    0.61
     Sars
    0.61
    POSITIVE LOGITS
     болезнь
    0.71
    ми
    0.63
    0
    0.63
    ні
    0.60
    ità
    0.58
     игру
    0.58
     králov
    0.57
     борь
    0.56
    0.55
     is
    0.55
    Activations Density 0.000%

    No Known Activations