© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14266
    Prev
    Next
    INDEX
    Explanations

    capital and financial contributions

    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
    U
    0.31
    راہیم
    0.29
    Privacy
    0.29
    隅
    0.29
    规则
    0.29
    Name
    0.28
     respons
    0.28
    OSR
    0.28
    N
    0.28
    の時間
    0.27
    POSITIVE LOGITS
     Kurn
    0.29
     Eld
    0.28
     Saka
    0.28
     Les
    0.28
     Sas
    0.28
     Barack
    0.28
    ecz
    0.27
     because
    0.27
     Sush
    0.27
     Gee
    0.27
    Activations Density 0.003%

    No Known Activations