© 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. 198687
    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
     thay
    0.46
    Dek
    0.45
    ](
    0.43
     देखील
    0.41
    Ak
    0.40
     c
    0.40
    Your
    0.39
     Sik
    0.38
     nie
    0.38
    Jeg
    0.38
    POSITIVE LOGITS
     నమో
    0.45
     IUnary
    0.45
    ᕝ
    0.42
    રાજ
    0.42
     पहलवान
    0.41
     evangelical
    0.40
     تصير
    0.40
    函数
    0.40
    搛
    0.40
    樣本
    0.39
    Activations Density 0.000%

    No Known Activations