© 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. 199624
    Prev
    Next
    INDEX
    Explanations

    international courts, law

    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
     Frog
    0.42
    Hình
    0.41
    Frog
    0.40
     Pioneer
    0.38
     Courtesy
    0.37
     appreciation
    0.37
     ③
    0.36
     श्रेष्ठ
    0.36
    ThemeProvider
    0.36
    ❸
    0.36
    POSITIVE LOGITS
     ICP
    0.48
    ICP
    0.42
     Quantum
    0.41
     LIC
    0.41
    量子
    0.40
     சர்
    0.40
    米的
    0.39
    哩
    0.38
    米
    0.38
    漉
    0.38
    Activations Density 0.001%

    No Known Activations