© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15113
    Prev
    Next
    INDEX
    Explanations

    и, есть

    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_13_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
    เป็น
    0.18
     crappy
    0.17
    ന്തപു
    0.17
     wrong
    0.16
    บน
    0.16
    ৩
    0.16
     ().
    0.16
    fix
    0.15
    ༽
    0.15
     klasik
    0.15
    POSITIVE LOGITS
     оте
    0.18
     halves
    0.17
    штейн
    0.17
     anys
    0.16
     championships
    0.16
    el
    0.16
    ޫ
    0.16
     створи
    0.16
    ст
    0.16
    وم
    0.16
    Activations Density 0.009%

    No Known Activations