© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214909
    Prev
    Next
    INDEX
    Explanations

    HTTP request handling

    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_31_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
     ব্রিটিশ
    0.42
     কক্ষে
    0.40
    embre
    0.39
     olabilir
    0.36
    propan
    0.36
     அறை
    0.36
    iam
    0.36
    クリーム
    0.36
    幄
    0.36
     habitaciones
    0.36
    POSITIVE LOGITS
     plurality
    0.39
     puzz
    0.36
    जल
    0.36
    乓
    0.36
    defn
    0.35
     mechanically
    0.35
    قر
    0.35
    Substring
    0.35
    னால
    0.34
     लाभार्थी
    0.34
    Activations Density 0.001%

    No Known Activations