© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78824
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_53_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
     dijel
    0.39
    、、、
    0.39
    钛
    0.39
    leigh
    0.38
    ebilirsiniz
    0.37
     participan
    0.36
    ojis
    0.35
    oom
    0.35
    irmingham
    0.34
     diverses
    0.34
    POSITIVE LOGITS
     ಅದ
    0.40
     Words
    0.40
    WORDS
    0.40
    ่ะ
    0.38
     Cor
    0.38
    Cor
    0.38
    鸢
    0.37
     Fossil
    0.37
    তাহাদের
    0.37
     இன்
    0.37
    Activations Density 0.000%

    No Known Activations