© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1121
    Prev
    Next
    INDEX
    Explanations

    patent

    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_44_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
    aysia
    0.40
    未知
    0.40
    Inscription
    0.38
    oples
    0.36
     કચ્છ
    0.35
    襟
    0.35
    AboutDlg
    0.35
    binom
    0.34
    pheus
    0.34
    滪
    0.34
    POSITIVE LOGITS
     patent
    3.56
     Patent
    3.22
     patents
    3.20
    Patent
    3.16
    patent
    3.16
    专利
    2.98
     Patents
    2.97
     patented
    2.81
     patente
    2.80
     PATENT
    2.64
    Activations Density 0.099%

    No Known Activations