© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129641
    Prev
    Next
    INDEX
    Explanations

    expert advice

    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_50_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
     merchandise
    0.39
     பத்திர
    0.38
     不过
    0.38
     arth
    0.37
     રાશિફળ
    0.37
    িনা
    0.36
     glory
    0.36
     महत्व
    0.36
    ┗
    0.36
    वरुन
    0.35
    POSITIVE LOGITS
     إس
    0.39
    فران
    0.39
     Callahan
    0.39
     irritating
    0.38
     Nowak
    0.37
    dep
    0.37
    வாக
    0.37
    زر
    0.36
    Dep
    0.36
    deps
    0.36
    Activations Density 0.004%

    No Known Activations