© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19617
    Prev
    Next
    INDEX
    Explanations

    causes or results in

    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_15_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
    يد
    0.62
     fibra
    0.58
    é
    0.57
     préférence
    0.56
     Hbdm
    0.55
     politici
    0.53
     ![](
    0.53
     Angaben
    0.52
     Eureka
    0.51
     préférences
    0.50
    POSITIVE LOGITS
    ↵↵
    0.55
     dense
    0.51
     excellence
    0.50
     abortion
    0.50
     exacerbated
    0.49
     low
    0.48
     производ
    0.48
     לצ
    0.48
    ↵
    0.47
     sprawling
    0.47
    Activations Density 0.046%

    No Known Activations