© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    adding to or replenishing

    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_13_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
    вр
    0.37
     Verl
    0.36
     społ
    0.35
    ｳ
    0.35
    ylmethylsulfanyl
    0.34
    イス
    0.33
    phenylsulfanyl
    0.33
     Mej
    0.33
    рила
    0.33
     साझे
    0.32
    POSITIVE LOGITS
     at
    0.38
    i
    0.36
     cuando
    0.36
     ($(
    0.35
    de
    0.35
    li
    0.34
     to
    0.34
    ．
    0.33
     when
    0.33
    .}(
    0.32
    Activations Density 0.053%

    No Known Activations