© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53623
    Prev
    Next
    INDEX
    Explanations

    your followed by benefit or descriptor

    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
     দেন
    0.38
    metik
    0.35
     obliterated
    0.33
     Leadership
    0.33
     Ambros
    0.33
     annealed
    0.33
    ಲ
    0.33
    ிர
    0.32
     شوی
    0.32
    itution
    0.32
    POSITIVE LOGITS
     Tah
    0.42
    列表
    0.40
    ]|
    0.40
    柺
    0.40
    Tah
    0.39
    chung
    0.38
    audience
    0.38
     ارسال
    0.38
     Md
    0.37
    欽
    0.36
    Activations Density 0.004%

    No Known Activations