© 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. 237425
    Prev
    Next
    INDEX
    Explanations

    Glass

    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
    étique
    0.45
    GOT
    0.42
     亻
    0.40
     !_
    0.40
     hvert
    0.40
    ceram
    0.39
     !$
    0.38
    อนไลน์
    0.37
    乇
    0.37
     ToString
    0.37
    POSITIVE LOGITS
    Helper
    0.42
    땔
    0.40
    Hel
    0.39
    Help
    0.38
     Helper
    0.38
    Hep
    0.38
    য়া
    0.37
    Eur
    0.37
     Roofing
    0.36
    mical
    0.35
    Activations Density 0.000%

    No Known Activations