© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18289
    Prev
    Next
    INDEX
    Explanations

    missile strikes

    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_15_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
    骁
    0.25
    買って
    0.24
    roar
    0.24
     przetwarz
    0.23
    ریز
    0.23
    几何
    0.23
    郭
    0.23
    웅
    0.23
     diseased
    0.23
    راتيج
    0.23
    POSITIVE LOGITS
     Mé
    0.31
     Animation
    0.29
     새
    0.29
     अके
    0.29
     Hig
    0.28
    é
    0.28
     Communication
    0.28
     наде
    0.28
     fashion
    0.27
     né
    0.27
    Activations Density 0.007%

    No Known Activations