© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226481
    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_10_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
    y
    0.57
    inig
    0.52
     zond
    0.49
    繧
    0.48
     രൂപ
    0.48
     vš
    0.47
    議員
    0.47
     opravdu
    0.47
    oq
    0.46
     vår
    0.46
    POSITIVE LOGITS
    дение
    0.44
     패턴
    0.43
     metastases
    0.43
     buckles
    0.42
     durée
    0.42
     flashes
    0.42
    대
    0.42
    История
    0.41
     Lys
    0.41
    𝚝
    0.41
    Activations Density 0.000%

    No Known Activations