© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200039
    Prev
    Next
    INDEX
    Explanations

    配件 accessory

    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_27_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
     Japón
    0.50
    僥
    0.50
    Sunglasses
    0.47
     ഇപ്പോള്‍
    0.47
     Fransiya
    0.47
    鬍
    0.47
    㗎
    0.47
    ფილი
    0.47
     következő
    0.47
    Tenemos
    0.47
    POSITIVE LOGITS
    +
    0.53
    0.51
     N
    0.50
     said
    0.47
     noted
    0.43
     creates
    0.43
    并
    0.43
    -
    0.43
     Se
    0.42
    2
    0.42
    Activations Density 0.000%

    No Known Activations