© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108399
    Prev
    Next
    INDEX
    Explanations

    ADCs

    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_2_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
    t
    2.41
    ب
    1.50
    ت
    1.49
    А
    1.23
    보
    1.14
    т
    1.11
    وی
    1.10
    전
    1.09
    >
    1.08
    ために
    1.06
    POSITIVE LOGITS
     ч
    1.09
     hypothes
    1.06
     дві
    1.05
     саме
    0.96
    ్రా
    0.96
    lighting
    0.96
     лока
    0.94
     прид
    0.94
     прикла
    0.94
     таки
    0.92
    Activations Density 0.001%

    No Known Activations