© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121679
    Prev
    Next
    INDEX
    Explanations

    registered agent applications

    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_3_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
    هم
    0.86
    ного
    0.65
    kte
    0.65
    ing
    0.61
    ä
    0.61
    ados
    0.58
    ب
    0.58
    ku
    0.57
    ublik
    0.57
    ة
    0.56
    POSITIVE LOGITS
     ແມ່ນ
    0.72
     purchasers
    0.70
     чувство
    0.68
     گے۔
    0.68
    ।
    0.67
     pięk
    0.66
    ।)
    0.64
     przyn
    0.64
    ↵↵
    0.64
     notas
    0.64
    Activations Density 0.003%

    No Known Activations