© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32957
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ক্র
    0.69
     크
    0.63
     кро
    0.62
     क्रा
    0.58
    크
    0.55
     кра
    0.53
     Cron
    0.53
    Crown
    0.52
     crows
    0.52
     Crown
    0.51
    POSITIVE LOGITS
     می‌ده
    0.42
     Sper
    0.41
    Corr
    0.41
     রাহ
    0.41
     Dir
    0.39
     sper
    0.39
     Mech
    0.38
     Corr
    0.38
    Mech
    0.37
    殚
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.