© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 239117
    Prev
    Next
    INDEX
    Explanations

    false negatives, code for, differences between

    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
     самой
    0.34
    ংকার
    0.34
     არის
    0.32
    Ს
    0.32
     طرز
    0.31
    Total
    0.31
     moniker
    0.31
     근
    0.30
     totalitarian
    0.30
    ाये
    0.30
    POSITIVE LOGITS
     crucially
    0.32
     mentally
    0.32
     Cour
    0.31
     Rockets
    0.30
     Cruises
    0.29
     Cork
    0.29
     plus
    0.28
    closing
    0.28
     Yates
    0.28
    while
    0.28
    Activations Density 0.001%

    No Known Activations