© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10237
    Prev
    Next
    INDEX
    Explanations

    margin:

    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_40_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
     Mickey
    0.40
     sparkling
    0.40
     تعدى
    0.37
     Sparkling
    0.37
     Kb
    0.36
    秽
    0.36
     जू
    0.36
     variable
    0.36
    扩大
    0.35
     अनियमित
    0.35
    POSITIVE LOGITS
     попа
    0.43
    mgmt
    0.40
     unos
    0.38
    দন
    0.38
     mgr
    0.38
    #![
    0.38
     manag
    0.37
    鏖
    0.37
    phosphorylation
    0.36
    睏
    0.36
    Activations Density 0.001%

    No Known Activations