© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178151
    Prev
    Next
    INDEX
    Explanations

    description or title placeholders

    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_24_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
    Allora
    0.41
    싶
    0.40
    ەد
    0.39
    品質
    0.39
    responding
    0.38
    linhas
    0.38
     نروح
    0.38
    ڻ
    0.38
    số
    0.37
    웬
    0.37
    POSITIVE LOGITS
     Weights
    0.46
     enfant
    0.44
     Manners
    0.42
     Cookbook
    0.40
     Work
    0.40
    pray
    0.39
     path
    0.39
     avances
    0.38
     mises
    0.37
     मंजिल
    0.37
    Activations Density 0.000%

    No Known Activations