© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150726
    Prev
    Next
    INDEX
    Explanations

    January 1, 1900/1970

    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_23_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
     algodón
    0.42
    淪
    0.42
    Variables
    0.39
    Algo
    0.39
     Corpus
    0.39
     víctimas
    0.38
    Abbreviations
    0.38
     víctima
    0.38
     zwycię
    0.38
    Partition
    0.37
    POSITIVE LOGITS
    埄
    0.39
    place
    0.39
    两条
    0.38
     му
    0.38
     purpose
    0.38
    idle
    0.37
     danach
    0.37
     follows
    0.37
    marine
    0.37
     হয়েছিলো
    0.37
    Activations Density 0.003%

    No Known Activations