© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36636
    Prev
    Next
    INDEX
    Explanations

    preparedness and readiness

    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_31_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
    εται
    0.22
     tru
    0.22
    詃
    0.21
     शी
    0.21
     레드
    0.21
    Tru
    0.21
    importance
    0.21
     Surely
    0.21
     venen
    0.21
     manten
    0.21
    POSITIVE LOGITS
    的情况下
    0.26
    已经是
    0.25
     ngunit
    0.24
    但是在
    0.24
     nhưng
    0.23
     لیکن
    0.23
     już
    0.22
    补
    0.21
     Nhưng
    0.21
    已经在
    0.21
    Activations Density 0.013%

    No Known Activations