© 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. 199813
    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
     pued
    0.36
     pochod
    0.35
     courtesy
    0.35
    ﺔ
    0.34
     approaches
    0.34
    trou
    0.34
    ९
    0.34
     Dund
    0.33
    Herz
    0.33
    िकी
    0.32
    POSITIVE LOGITS
    Ⲁ
    0.37
     camisa
    0.35
    南北
    0.34
    렜
    0.34
     Romans
    0.33
    yaa
    0.33
    家伙
    0.33
    arem
    0.32
     ajustar
    0.32
     канале
    0.31
    Activations Density 0.000%

    No Known Activations