© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136160
    Prev
    Next
    INDEX
    Explanations

    catalytic activity

    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_12_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
    🧿
    0.55
    🥸
    0.52
    🧨
    0.52
     Pusenkoff
    0.52
    𝙞
    0.51
     ぐらい
    0.50
    Ẓ
    0.50
     அவனே
    0.49
     "$"
    0.49
    (",")
    0.49
    POSITIVE LOGITS
    CNC
    0.62
     paid
    0.55
    Mini
    0.50
    els
    0.50
     borrower
    0.50
    ;
    0.49
    bat
    0.48
     pumped
    0.48
    k
    0.48
     (
    0.48
    Activations Density 0.001%

    No Known Activations