© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143283
    Prev
    Next
    INDEX
    Explanations

    CREATE

    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
    Not in Any Lists

    No Comments

    Negative Logits
     minis
    0.47
     sequenced
    0.43
    ਦ
    0.40
    lade
    0.40
     tabled
    0.39
     disk
    0.39
     DRM
    0.39
    MLElement
    0.38
    ගත්
    0.38
     threaded
    0.37
    POSITIVE LOGITS
     निवार
    0.40
     މަ
    0.39
    侵
    0.37
     κατο
    0.37
     Niet
    0.37
     Qu
    0.37
    官
    0.36
     Ν
    0.36
     Quarantine
    0.36
     Matt
    0.35
    Activations Density 0.001%

    No Known Activations