© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83964
    Prev
    Next
    INDEX
    Explanations

    authors and academic texts

    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_29_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
     ਅਤੇ
    0.58
     और
    0.57
     आणि
    0.56
     மற்றும்
    0.55
     અને
    0.53
     һәм
    0.52
     және
    0.52
     আৰু
    0.52
     ۽
    0.52
     మరియు
    0.51
    POSITIVE LOGITS
     triggered
    0.38
     problème
    0.37
     lef
    0.36
     Lots
    0.35
    triggered
    0.35
    leh
    0.32
     BLE
    0.31
    どんどん
    0.31
     Lot
    0.31
    ingresso
    0.31
    Activations Density 0.000%

    No Known Activations