© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215061
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    矜
    0.42
    太多
    0.39
    ờ
    0.39
    这么多
    0.38
    ajjati
    0.37
    ่ง
    0.36
    啜
    0.36
    เตอร์
    0.36
    ঙ্গিক
    0.36
    喫
    0.35
    POSITIVE LOGITS
     хорошее
    0.47
     maz
    0.46
     rockets
    0.45
     hive
    0.44
     GOOD
    0.43
    집합
    0.43
     hives
    0.41
     Tres
    0.40
     good
    0.40
    laut
    0.39
    Activations Density 0.004%

    No Known Activations