© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208430
    Prev
    Next
    INDEX
    Explanations

    log messages with timestamps

    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_25_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
     bridle
    0.41
    يكية
    0.38
    洄
    0.38
    StartPosition
    0.38
     carry
    0.38
     اجمع
    0.38
     quadru
    0.37
     দখল
    0.37
    iscale
    0.37
     divisi
    0.36
    POSITIVE LOGITS
     Испа
    0.40
     😀
    0.38
    🚲
    0.38
     Фото
    0.38
     Име
    0.36
     Сайт
    0.36
    炜
    0.36
     вчера
    0.36
     😂
    0.35
     জানা
    0.35
    Activations Density 0.001%

    No Known Activations