© 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. 237432
    Prev
    Next
    INDEX
    Explanations

    IEEE

    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
     sechs
    0.37
    american
    0.37
    AW
    0.36
     Wein
    0.36
    붐
    0.36
    APs
    0.35
    plicht
    0.35
    Warner
    0.35
     Kessler
    0.35
    Sixth
    0.35
    POSITIVE LOGITS
     cannibal
    0.45
     innocence
    0.44
     الدراسي
    0.42
     الج
    0.40
     aliqu
    0.40
     inoculated
    0.39
    icarboxylic
    0.39
     pointed
    0.38
    ီ
    0.38
     idempot
    0.38
    Activations Density 0.002%

    No Known Activations