© 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. 143727
    Prev
    Next
    INDEX
    Explanations

    HashiCorp tools

    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
     adjust
    0.38
     spurs
    0.38
     spur
    0.37
     డబ్బు
    0.37
     nitro
    0.37
     Ideas
    0.37
     reali
    0.36
    硝
    0.36
     Inclusive
    0.36
     Chili
    0.36
    POSITIVE LOGITS
     Tic
    0.44
    Craft
    0.44
    Tic
    0.40
    Yard
    0.39
    Storage
    0.39
    ссмо
    0.38
    ytoin
    0.38
    loff
    0.37
     বঙ্গ
    0.37
    conde
    0.37
    Activations Density 0.001%

    No Known Activations