© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122523
    Prev
    Next
    INDEX
    Explanations

    list item phrases

    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_38_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
    助
    0.55
     assisting
    0.51
    assist
    0.49
     assists
    0.47
     помога
    0.46
     aiding
    0.46
     通知
    0.44
     assist
    0.44
     मदत
    0.43
    协助
    0.43
    POSITIVE LOGITS
    蹼
    0.45
     handleSubmit
    0.42
    Χ
    0.42
     ausges
    0.38
     Calculated
    0.37
     represented
    0.36
     jí
    0.35
     problème
    0.35
    రుగు
    0.35
    指令
    0.35
    Activations Density 0.004%

    No Known Activations