© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163530
    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_31_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
    𝐑
    0.38
     Sl
    0.38
     steps
    0.37
    蝋
    0.37
     kesulitan
    0.37
     Analog
    0.37
     Dollar
    0.36
     Brad
    0.36
    Rag
    0.36
     Suzuki
    0.36
    POSITIVE LOGITS
    也有
    0.36
     parcial
    0.35
     ahí
    0.34
     "-
    0.34
    embre
    0.34
    格局
    0.34
     up
    0.34
     व्यास
    0.34
     எப்போதும்
    0.34
     preju
    0.34
    Activations Density 0.000%

    No Known Activations