© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196700
    Prev
    Next
    INDEX
    Explanations

    `System.Collections.Generic`

    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_27_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
     concaten
    0.36
     메서
    0.36
     appending
    0.35
     arithmetic
    0.34
     exceeding
    0.34
     れ
    0.32
     Mehmet
    0.32
    赅
    0.32
    ')],
    0.32
     regularization
    0.31
    POSITIVE LOGITS
    íg
    0.43
     देखने
    0.38
    쭉
    0.37
    众多
    0.36
    श्री
    0.36
     diyor
    0.35
    参观
    0.35
    رويج
    0.35
    day
    0.35
    之所以
    0.35
    Activations Density 0.000%

    No Known Activations