© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171045
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     এদেশে
    0.46
     कराय
    0.40
     ContentView
    0.40
    तर
    0.39
     అ
    0.38
     understands
    0.38
     ತುಂಬಾ
    0.37
    شه
    0.37
    ادات
    0.37
     tabBar
    0.37
    POSITIVE LOGITS
     ?
    0.52
    ​
    0.50
    ?$
    0.47
    ?",
    0.46
    もしくは
    0.46
    ​,
    0.45
    ?</
    0.44
     ?”
    0.44
     BEST
    0.44
     ؟
    0.44
    Activations Density 0.004%

    No Known Activations