© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121235
    Prev
    Next
    INDEX
    Explanations

    test, train, folder, csv

    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_27_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
    πισ
    0.39
     Levit
    0.38
    经过
    0.38
     expectativa
    0.38
     expectativas
    0.37
    ньше
    0.37
    敉
    0.36
    极
    0.36
     αντα
    0.36
     مدد
    0.36
    POSITIVE LOGITS
     G
    0.41
     Snake
    0.39
     RA
    0.35
     Bhopal
    0.34
     Remove
    0.34
     Bunny
    0.34
     Rename
    0.34
     n
    0.33
     tatt
    0.33
     rene
    0.33
    Activations Density 0.001%

    No Known Activations