© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215148
    Prev
    Next
    INDEX
    Explanations

    words like better, entirely, ambition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
     string
    0.56
     toler
    0.53
     planche
    0.52
     bilateral
    0.49
    9
    0.49
     svoj
    0.47
     sores
    0.47
     qualific
    0.47
     tell
    0.46
     itse
    0.46
    POSITIVE LOGITS
    のです
    0.53
    тировать
    0.51
     बोलेंगे
    0.51
    लाल
    0.50
     ändern
    0.49
    ो
    0.49
    robi
    0.48
    ホル
    0.48
    Ղ
    0.47
    ｔ
    0.47
    Activations Density 0.000%

    No Known Activations