© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54730
    Prev
    Next
    INDEX
    Explanations

    in- or en- prefix

    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_30_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
    *:
    0.38
     adres
    0.38
     шт
    0.37
    べて
    0.37
     experiencing
    0.36
     ঠিকানা
    0.36
    pupp
    0.36
    asem
    0.36
    neighbours
    0.36
    producing
    0.35
    POSITIVE LOGITS
     cannibal
    0.42
     క్రి
    0.37
    țiile
    0.36
     cond
    0.35
     ""<
    0.35
     khat
    0.35
     ${(
    0.34
     confines
    0.34
    タリー
    0.34
     genial
    0.33
    Activations Density 0.004%

    No Known Activations