© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82284
    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_0_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
     تک
    0.58
    .`);
    0.56
    ב
    0.55
    nbsp
    0.55
    ut
    0.54
    oretical
    0.54
    ¹.
    0.52
    gunakan
    0.51
    niest
    0.50
     Щ
    0.50
    POSITIVE LOGITS
    ارا
    0.52
     parable
    0.50
    किला
    0.46
     základě
    0.46
    ارہ
    0.46
     bảy
    0.46
    ೇಶ್
    0.45
    坤
    0.45
    اد
    0.44
    aren
    0.43
    Activations Density 0.000%

    No Known Activations