© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30940
    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
    憂
    0.37
     Bldg
    0.37
     কবে
    0.36
    ឃើញ
    0.35
     benzene
    0.34
     valamint
    0.34
     Марафон
    0.34
    骛
    0.34
     BSTC
    0.34
     desplaz
    0.34
    POSITIVE LOGITS
     soit
    0.38
    Accuracy
    0.38
    sej
    0.37
    Public
    0.35
     score
    0.35
    academic
    0.34
    insky
    0.34
    agogue
    0.34
     lus
    0.34
     determinados
    0.34
    Activations Density 0.000%

    No Known Activations