© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    Qt alignment and window flags

    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_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
    re
    0.64
    m
    0.59
    ones
    0.58
    v
    0.57
    at
    0.56
    com
    0.55
    id
    0.55
    de
    0.54
    new
    0.54
    ↵
    0.53
    POSITIVE LOGITS
     கல்லூ
    0.66
    ᛁ
    0.65
     школу
    0.60
     Omphalodes
    0.60
    ৮
    0.60
     CCOC
    0.60
     SOD
    0.60
     Sod
    0.59
     Leibn
    0.59
     dielectric
    0.59
    Activations Density 0.007%

    No Known Activations