© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198080
    Prev
    Next
    INDEX
    Explanations

    web components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    чить
    0.44
    чила
    0.44
    Rav
    0.41
    䇝
    0.41
    ⃖
    0.39
    рку
    0.38
     scrollTo
    0.37
     گی۔
    0.37
     eingestellt
    0.37
    刚
    0.37
    POSITIVE LOGITS
    shar
    0.43
     Dign
    0.43
     Lunar
    0.41
     cob
    0.40
     Seven
    0.40
     संभा
    0.39
    Shar
    0.39
    ences
    0.39
    Lunar
    0.38
    seven
    0.38
    Activations Density 0.000%

    No Known Activations