© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28937
    Prev
    Next
    INDEX
    Explanations

    clustering parameters

    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
     池
    0.41
     চিঠি
    0.40
    anean
    0.38
     treaty
    0.37
     Daniele
    0.36
     raving
    0.36
    рати
    0.36
    არის
    0.36
    ==============
    0.35
    хими
    0.35
    POSITIVE LOGITS
    łość
    0.40
     رنز
    0.38
    Przyp
    0.38
    बर्ग
    0.37
    暮らし
    0.37
     Put
    0.37
    পদ
    0.37
     put
    0.36
     dé
    0.36
     kalk
    0.36
    Activations Density 0.001%

    No Known Activations