© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211896
    Prev
    Next
    INDEX
    Explanations

    ending at, in

    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_20_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
     overview
    0.46
    -\\
    0.44
     deduction
    0.41
     Stitch
    0.40
     reconst
    0.40
     photocon
    0.40
     laboral
    0.40
     from
    0.39
     embroidery
    0.39
    張り
    0.39
    POSITIVE LOGITS
    增速
    0.48
    यदि
    0.44
    तिया
    0.44
    琇
    0.44
     душу
    0.44
     насы
    0.43
     kū
    0.43
     إذا
    0.42
     smack
    0.41
    ंजक
    0.40
    Activations Density 0.000%

    No Known Activations