© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106994
    Prev
    Next
    INDEX
    Explanations

    EXT followed by scene descriptions or extreme

    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
    Negative Logits
    。
    1.20
    ।
    1.03
    ，
    1.03
    2
    1.02
    ২০
    0.95
     kurzer
    0.93
    al
    0.92
    เป็น
    0.90
    O
    0.89
    ।)
    0.88
    POSITIVE LOGITS
    ק
    1.62
    0
    1.30
    ب
    1.28
    ного
    1.23
    ни
    1.20
     Abelian
    1.15
    на
    1.07
    ן
    1.06
    ن
    1.05
    та
    1.03
    Activations Density 0.001%

    No Known Activations