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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90612
    Prev
    Next
    INDEX
    Explanations

    Problem

    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_60_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
     so
    0.58
    #
    0.43
     Legacy
    0.42
     her
    0.40
     Idea
    0.39
     centers
    0.38
    kup
    0.38
     называ
    0.37
     if
    0.37
     pe
    0.37
    POSITIVE LOGITS
     hypersur
    0.38
     খুবই
    0.36
    hauer
    0.36
    ismod
    0.36
     وطالبات
    0.36
    很
    0.35
    isées
    0.34
     худо
    0.34
     очень
    0.34
    patial
    0.34
    Activations Density 0.000%

    No Known Activations