© 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. 196772
    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
    ಡುಗೆ
    0.44
     Sá
    0.42
     enacting
    0.39
    classteacher
    0.39
     anch
    0.39
    彝
    0.39
    african
    0.38
    ভাগে
    0.38
     사는
    0.38
     domino
    0.38
    POSITIVE LOGITS
    kin
    0.42
    ремен
    0.42
     ED
    0.39
    煽
    0.37
     धक्का
    0.36
    rau
    0.35
     Razer
    0.35
    go
    0.35
    otin
    0.35
     যোদ্ধ
    0.35
    Activations Density 0.000%

    No Known Activations