© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200296
    Prev
    Next
    INDEX
    Explanations

    consistent

    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_6_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
    ä
    1.22
     fainting
    0.85
    trä
    0.84
    س
    0.82
    "。
    0.79
    近年来
    0.74
    ס
    0.73
    冏
    0.71
    რ
    0.71
     kā
    0.71
    POSITIVE LOGITS
    2
    1.52
    1
    1.30
    G
    1.09
    O
    1.02
    6
    1.01
    F
    1.00
    4
    1.00
    3
    0.97
     bọn
    0.93
    I
    0.93
    Activations Density 0.003%

    No Known Activations