© 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. 30731
    Prev
    Next
    INDEX
    Explanations

    fr variants

    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
     ভাস
    0.40
    hag
    0.39
    Subscription
    0.39
    subscriptions
    0.39
    passport
    0.38
    subscribe
    0.37
    subscription
    0.36
    opian
    0.35
    <unused64>
    0.35
    וני
    0.35
    POSITIVE LOGITS
     فر
    1.74
     fr
    1.52
     Fr
    1.46
     الفر
    1.46
    Fr
    1.44
    fr
    1.35
    فر
    1.27
     FR
    1.27
    FR
    1.16
     फ्र
    1.10
    Activations Density 0.004%

    No Known Activations