© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102901
    Prev
    Next
    INDEX
    Explanations

    .tolist()

    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_14_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
     R
    0.70
    ed
    0.61
    ich
    0.61
     quien
    0.60
     quienes
    0.60
     sa
    0.54
     ;
    0.53
     who
    0.52
     estos
    0.51
     equipo
    0.51
    POSITIVE LOGITS
    addKill
    0.54
    قافة
    0.53
    叁
    0.53
     UHF
    0.52
     Hfn
    0.52
    Thr
    0.52
     말고
    0.51
     الد
    0.50
    匚
    0.50
     مت
    0.49
    Activations Density 0.005%

    No Known Activations