© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213792
    Prev
    Next
    INDEX
    Explanations

    Czech Republic

    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
     इंस्टीट्यूट
    0.45
    Ĩ
    0.41
    ESA
    0.39
     Valuation
    0.39
     negative
    0.39
     fortunately
    0.39
     Institute
    0.39
    Institute
    0.39
     जोन
    0.38
    सीएल
    0.38
    POSITIVE LOGITS
    पीडी
    0.38
     Stahl
    0.37
     Nigam
    0.37
    黟
    0.37
     Pascal
    0.36
    subsetneq
    0.36
    oclip
    0.36
    력
    0.36
    SetFloat
    0.35
     얘
    0.35
    Activations Density 0.001%

    No Known Activations