© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34930
    Prev
    Next
    INDEX
    Explanations

    road names and directions

    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_11_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
     Prevention
    0.59
     باسکٹ
    0.54
     Затем
    0.54
     Б
    0.53
     pesante
    0.53
     Cottage
    0.52
    ;
    0.52
    überküloz
    0.52
     प्लान
    0.51
     ڈپ
    0.51
    POSITIVE LOGITS
    ラ
    0.74
    車
    0.70
    车
    0.58
    リ
    0.57
    ถนน
    0.55
    ıları
    0.54
     electoral
    0.54
    lades
    0.53
    ﾗ
    0.53
    حه
    0.52
    Activations Density 0.016%

    No Known Activations