© 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. 18363
    Prev
    Next
    INDEX
    Explanations

    again

    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
     یکی
    0.58
     новые
    0.55
    ulner
    0.54
     новая
    0.53
     nueva
    0.50
     biasa
    0.49
     ت
    0.49
     भारता
    0.48
     لخ
    0.48
     cilia
    0.47
    POSITIVE LOGITS
    रित
    0.55
    تدائي
    0.52
     Fran
    0.49
    混
    0.48
     Except
    0.48
    க்கொள்ள
    0.47
    場所
    0.47
     instruct
    0.47
    UED
    0.46
    稿
    0.46
    Activations Density 0.001%

    No Known Activations