© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65373
    Prev
    Next
    INDEX
    Explanations

    shared

    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
    ểm
    0.45
     Background
    0.41
     à
    0.39
     Pine
    0.38
     Coelho
    0.38
     Tut
    0.38
     செய்த
    0.38
     Tutak
    0.37
     Bos
    0.37
     Examination
    0.36
    POSITIVE LOGITS
     reality
    0.44
    ज़ी
    0.38
     раздра
    0.38
    Reality
    0.37
    VICES
    0.37
    빤
    0.37
    reality
    0.37
    tempCard
    0.36
     საჭ
    0.36
    ිරීම
    0.35
    Activations Density 0.004%

    No Known Activations