© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164556
    Prev
    Next
    INDEX
    Explanations

    how important each is

    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_31_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
    ของการ
    0.48
     của
    0.44
     của
    0.42
     של
    0.40
    Sink
    0.39
    ของผู้
    0.38
    MenuList
    0.37
    播
    0.37
    प्रभात
    0.36
    宿
    0.36
    POSITIVE LOGITS
     noticing
    0.38
    UNRELATED
    0.37
     ആള
    0.36
     agréable
    0.36
     temporary
    0.36
    据
    0.35
     نار
    0.35
     };
    0.35
    enberg
    0.35
     Ос
    0.34
    Activations Density 0.008%

    No Known Activations