© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237342
    Prev
    Next
    INDEX
    Explanations

    section headings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     certo
    0.40
    str
    0.39
     bodyguard
    0.39
     哈
    0.37
    níku
    0.37
    arde
    0.36
    breeds
    0.36
     яко
    0.36
     sacc
    0.35
     breed
    0.35
    POSITIVE LOGITS
     Gif
    0.39
     drain
    0.39
    ✞
    0.39
     drains
    0.38
     protobuf
    0.38
    劇
    0.38
     उल्लेख
    0.38
     numérica
    0.37
    hubung
    0.37
    軎
    0.37
    Activations Density 0.002%

    No Known Activations