© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91572
    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
    ୯
    0.51
     Emperors
    0.50
     as
    0.49
    BtnUp
    0.47
     Eton
    0.46
     ウ
    0.45
     INST
    0.45
     ദേശ
    0.45
     グリーン
    0.45
     সম্রাট
    0.45
    POSITIVE LOGITS
    राबरी
    0.49
    বাহিনীর
    0.49
     mendapatkan
    0.48
    akukan
    0.47
    ament
    0.46
    货币
    0.46
    j
    0.46
    anın
    0.45
    ባል
    0.45
    yeri
    0.44
    Activations Density 0.000%

    No Known Activations