© 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. 8620
    Prev
    Next
    INDEX
    Explanations

    potential harm or danger

    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
    스
    0.22
    Girl
    0.20
    ス
    0.20
     ಸ್
    0.18
    r
    0.18
    尔
    0.18
    ber
    0.18
    Bottom
    0.18
    斯
    0.18
    श
    0.18
    POSITIVE LOGITS
     посо
    0.20
     toekom
    0.20
     interfere
    0.19
     عادة
    0.19
     aiutare
    0.19
     dessas
    0.18
    攔
    0.18
     पाण्याच्या
    0.17
     desse
    0.17
     batteria
    0.17
    Activations Density 0.122%

    No Known Activations