© 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. 52773
    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
    property
    0.38
     Herrn
    0.38
    estate
    0.38
    ترى
    0.38
    📜
    0.38
    rider
    0.37
     donated
    0.36
    قدر
    0.36
    రోజు
    0.36
     Herr
    0.35
    POSITIVE LOGITS
     अन्
    0.42
     Prag
    0.40
     Incorpor
    0.40
     Cabot
    0.40
     свето
    0.39
     Nauka
    0.39
     incorpor
    0.38
     Degrad
    0.38
     Crear
    0.37
    喚
    0.37
    Activations Density 0.000%

    No Known Activations