© 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. 197082
    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
    チョコレート
    0.41
    Malaysia
    0.38
    थे
    0.37
    🍫
    0.37
    頴
    0.37
    Means
    0.37
    ړ
    0.36
    થે
    0.36
     रामबा
    0.36
     भु
    0.35
    POSITIVE LOGITS
     건
    0.42
    )|^
    0.41
    urri
    0.40
     apert
    0.40
    誼
    0.39
     ORD
    0.38
     midterm
    0.38
     টিক্কা
    0.38
    tick
    0.37
    裄
    0.37
    Activations Density 0.000%

    No Known Activations