© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120047
    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_27_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
     मजबूर
    0.40
     CB
    0.39
     wybor
    0.39
     👋
    0.38
     божомолдор
    0.36
    등학교
    0.36
    Notably
    0.36
     सामान्य
    0.36
    Ⲓ
    0.36
     wrongful
    0.35
    POSITIVE LOGITS
     soil
    0.37
     طریق
    0.36
    ދ
    0.34
    taste
    0.34
     propriedade
    0.33
    jari
    0.33
     PUC
    0.33
    机会
    0.33
    posti
    0.33
    urch
    0.33
    Activations Density 0.000%

    No Known Activations