© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89595
    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_11_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
    hiya
    0.56
    рті
    0.52
     lignes
    0.51
    オプション
    0.49
    蕎
    0.45
     doesn
    0.44
     więc
    0.44
    ﮨ
    0.44
     ハン
    0.44
     빅뱅
    0.43
    POSITIVE LOGITS
    ture
    0.48
    turquoise
    0.46
    彩色
    0.44
    heatmap
    0.43
    odnev
    0.43
    uscular
    0.42
     slippery
    0.42
    បែប
    0.42
     ATI
    0.42
    ل
    0.42
    Activations Density 0.000%

    No Known Activations