© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141390
    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_12_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
    T
    0.32
    MAC
    0.31
    D
    0.29
    V
    0.29
     illustrating
    0.29
    INA
    0.27
     одном
    0.27
    AR
    0.27
     ه
    0.27
    بعة
    0.26
    POSITIVE LOGITS
     momenti
    0.30
     leyes
    0.29
     Robins
    0.28
     transgression
    0.28
    ки
    0.27
     Sponge
    0.27
     rights
    0.27
    ments
    0.27
     Cookie
    0.27
    чих
    0.27
    Activations Density 0.000%

    No Known Activations