© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16205
    Prev
    Next
    INDEX
    Explanations

    Leonardo.AI

    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_15_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
    gly
    0.51
     الاست
    0.48
     nadi
    0.48
     menyel
    0.47
     wú
    0.47
    㥉
    0.47
     desempenho
    0.46
     را
    0.46
     rendu
    0.46
    ambulance
    0.45
    POSITIVE LOGITS
    Still
    0.53
     Juan
    0.49
     C
    0.49
     Anyway
    0.49
     John
    0.48
     Networks
    0.48
    Thank
    0.47
     बैठे
    0.47
     Canterbury
    0.47
    John
    0.46
    Activations Density 0.000%

    No Known Activations