© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176619
    Prev
    Next
    INDEX
    Explanations

    依山尽

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     stockpile
    0.25
    ുകൊണ്ടാണ്
    0.23
    켠
    0.22
    っぱい
    0.22
    jsx
    0.22
     kodu
    0.21
    য়াল
    0.21
     compel
    0.21
    iams
    0.21
     toxins
    0.21
    POSITIVE LOGITS
    !}
    0.27
    并且
    0.25
    iberg
    0.25
     அட்ட
    0.24
     அழு
    0.24
    !»
    0.23
     இரா
    0.23
     없고
    0.23
     있고
    0.23
     Analyse
    0.23
    Activations Density 0.032%

    No Known Activations