© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212008
    Prev
    Next
    INDEX
    Explanations

    VA benefits, education benefits, Cultural Bureau

    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_20_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
     چپ
    0.46
     Gala
    0.45
     ionized
    0.45
     Thanksgiving
    0.43
    gev
    0.43
     Tray
    0.43
     through
    0.42
     marvel
    0.42
     washed
    0.42
     m
    0.42
    POSITIVE LOGITS
    сторінку
    0.45
    Histor
    0.44
     สืบค้นเมื่อ
    0.43
     Occurrence
    0.42
    წერ
    0.42
     furtherance
    0.42
     historie
    0.41
    songwriter
    0.41
    ضمن
    0.41
    ผู้ชมในสนาม
    0.41
    Activations Density 0.000%

    No Known Activations