© 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. 215187
    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
    ަން
    0.46
     اف
    0.41
    霊
    0.41
     MM
    0.41
     Mende
    0.40
     "=
    0.39
     Phosphorus
    0.39
     allé
    0.38
    仓
    0.37
    𝙢
    0.37
    POSITIVE LOGITS
     eventual
    0.40
    Kod
    0.40
    jobs
    0.40
    orm
    0.39
    grace
    0.39
    cesa
    0.38
     graceful
    0.38
    Jobs
    0.38
    COD
    0.37
     jobs
    0.37
    Activations Density 0.000%

    No Known Activations