© 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. 57841
    Prev
    Next
    INDEX
    Explanations

    tech and gadget reviews

    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_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
    ED
    0.71
    el
    0.61
    ？
    0.57
    Old
    0.56
    MI
    0.56
    IG
    0.55
    MAR
    0.54
    ：
    0.53
    Ed
    0.51
    Co
    0.51
    POSITIVE LOGITS
     класу
    0.58
    ні
    0.57
     handcuffed
    0.54
    ೂರ್ಯ
    0.54
     tia
    0.53
     বাসা
    0.52
     яка
    0.51
    ﹰ
    0.50
     частина
    0.49
    л
    0.49
    Activations Density 0.027%

    No Known Activations