© 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. 62648
    Prev
    Next
    INDEX
    Explanations

    add more

    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
     y
    0.58
    ﻛ
    0.58
     cabe
    0.53
    olve
    0.52
     utilizada
    0.51
     cuyas
    0.51
     cuyos
    0.50
     don
    0.49
     وقع
    0.49
     yh
    0.49
    POSITIVE LOGITS
     enemies
    0.63
    ール
    0.63
    हरु
    0.60
    다
    0.60
     reforms
    0.59
     incompatibility
    0.57
     amplitud
    0.56
    uetooth
    0.55
     innovations
    0.53
    ون
    0.53
    Activations Density 0.017%

    No Known Activations