© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45027
    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_22_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
    ]).
    0.45
     网络
    0.44
     ܕ
    0.41
    架构
    0.41
    intent
    0.40
     a
    0.40
    內容
    0.40
    產品
    0.40
    子ども
    0.40
     Susp
    0.39
    POSITIVE LOGITS
     getan
    0.53
     betracht
    0.50
     Sonu
    0.47
     cerr
    0.46
     hindu
    0.46
     vyh
    0.45
     trouve
    0.45
     sieht
    0.45
    JTextField
    0.44
     finde
    0.44
    Activations Density 0.000%

    No Known Activations