© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132061
    Prev
    Next
    INDEX
    Explanations

    JPEG DCT quantization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
    >∕</
    0.44
    unpack
    0.41
    Git
    0.39
    fasc
    0.39
    Nit
    0.39
    Hydrogen
    0.38
    ፃ
    0.38
    साल
    0.38
     Brennan
    0.38
    خ
    0.38
    POSITIVE LOGITS
     Blocks
    0.53
    塊
    0.53
     JPG
    0.50
     DCT
    0.50
     blocks
    0.49
    块
    0.49
     J
    0.49
    Blocks
    0.48
     блоков
    0.48
     JPEG
    0.47
    Activations Density 0.015%

    No Known Activations