© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246853
    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_40_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
     lubricant
    0.41
     lubricants
    0.41
    နယ်
    0.39
    াইবার
    0.38
     стиля
    0.38
    acula
    0.38
    たつ
    0.38
    乙
    0.37
    交
    0.36
     Morav
    0.36
    POSITIVE LOGITS
     Philippe
    0.41
    γγελ
    0.39
     ph
    0.39
     प्रत्य
    0.38
     Physi
    0.38
    ゲ
    0.38
     fisi
    0.38
    гән
    0.38
     intelligente
    0.38
    તુ
    0.37
    Activations Density 0.000%

    No Known Activations