© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74598
    Prev
    Next
    INDEX
    Explanations

    arrival &

    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
    Negative Logits
     ہاکی
    0.43
     bước
    0.40
    騾
    0.38
     zakład
    0.38
     via
    0.38
     는
    0.37
     commencent
    0.37
    ثمار
    0.37
    via
    0.37
     먼저
    0.36
    POSITIVE LOGITS
     misrepresented
    0.41
     jeweil
    0.39
    𝖔
    0.39
    pré
    0.37
     Xiu
    0.37
    செ
    0.37
     Mili
    0.37
     sizeof
    0.36
     setSelected
    0.36
    ermat
    0.36
    Activations Density 0.004%

    No Known Activations