© 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
    2. Gemma-3-27B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-262K
    4. 109920
    Prev
    Next
    INDEX
    Explanations

    andriod

    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_2_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
    你
    1.27
    ли
    1.02
    you
    1.01
    주
    0.99
    데이트
    0.98
    보
    0.98
    of
    0.97
     Elektrokh
    0.97
    ==
    0.97
    х
    0.95
    POSITIVE LOGITS
    inis
    0.98
    ink
    0.92
    ang
    0.91
    ivering
    0.91
    ographic
    0.91
    han
    0.87
     l
    0.84
    ilor
    0.83
    inizi
    0.83
     bör
    0.81
    Activations Density 0.001%

    No Known Activations