© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54920
    Prev
    Next
    INDEX
    Explanations

    pastoral meetings or soluble salts

    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_30_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
     ":
    0.42
    うま
    0.39
     lined
    0.39
    远离
    0.37
    і
    0.37
     worldwide
    0.36
     expanding
    0.36
     obstacles
    0.35
     restorative
    0.35
     transformations
    0.35
    POSITIVE LOGITS
     instar
    0.42
     mols
    0.41
    כּ
    0.40
    AGUE
    0.39
     やす
    0.39
    ವಿಧ
    0.38
    Aye
    0.38
     IG
    0.38
     IntelliJ
    0.37
    𝗡
    0.37
    Activations Density 0.000%

    No Known Activations