© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156797
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    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_50_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
     ho
    0.76
    ho
    0.64
    Ho
    0.61
     Ho
    0.58
     хо
    0.51
    hoz
    0.51
     hozz
    0.51
    호
    0.50
    hov
    0.46
    хов
    0.45
    POSITIVE LOGITS
    兵
    0.39
     المرس
    0.38
    సం
    0.38
     harb
    0.38
     binding
    0.38
     Enrico
    0.37
    妤
    0.37
    Binding
    0.36
    duction
    0.36
     jay
    0.36
    Activations Density 0.004%

    No Known Activations