© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44439
    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_13_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
    en
    0.68
    w
    0.60
    un
    0.58
    le
    0.57
    ue
    0.57
    affe
    0.54
    ear
    0.52
    one
    0.52
    el
    0.52
    ul
    0.51
    POSITIVE LOGITS
     зону
    0.61
     сексуа
    0.60
     новости
    0.58
    ص
    0.57
     conjunto
    0.55
     разви
    0.53
     б
    0.52
    ７
    0.52
    公開
    0.52
    タン
    0.51
    Activations Density 0.000%

    No Known Activations