© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51372
    Prev
    Next
    INDEX
    Explanations

    HOA management software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Huffington
    0.36
     Victorian
    0.36
    ADIAN
    0.36
     Elegant
    0.34
    历
    0.34
     पढ़ी
    0.33
     Slice
    0.33
     योग
    0.33
     Door
    0.33
    Door
    0.33
    POSITIVE LOGITS
    電流
    0.40
     boson
    0.39
     CPUs
    0.39
     wiring
    0.36
    aspid
    0.35
     Wiring
    0.35
    STRUCT
    0.35
     वायरिंग
    0.34
     전류
    0.34
    ऩ
    0.34
    Activations Density 0.006%

    No Known Activations