© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66184
    Prev
    Next
    INDEX
    Explanations

    P.S. postscript

    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_41_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
    靣
    0.40
    梂
    0.39
     கூறுக
    0.38
    Namespace
    0.37
     rpg
    0.37
    ห์
    0.36
     zn
    0.36
    picker
    0.36
    RPG
    0.36
    Repo
    0.35
    POSITIVE LOGITS
     PS
    1.83
    PS
    1.57
     ps
    1.33
     Ps
    1.23
    ps
    1.14
     P
    1.11
     post
    1.11
     p
    0.94
    Ps
    0.93
    पीएस
    0.89
    Activations Density 0.003%

    No Known Activations