© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29603
    Prev
    Next
    INDEX
    Explanations

    array initialization

    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_40_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
     ample
    0.38
     padr
    0.36
    糠
    0.36
    leck
    0.35
    ცა
    0.35
     pob
    0.35
     neurologic
    0.34
     goodwill
    0.33
     Luck
    0.33
    ስት
    0.33
    POSITIVE LOGITS
     LENGTH
    0.42
     comprimento
    0.41
     QTreeWidgetItem
    0.41
     tây
    0.39
     सब्सक्राइब
    0.38
    䧉
    0.38
     length
    0.38
     വിള
    0.37
     lengths
    0.37
     słu
    0.37
    Activations Density 0.002%

    No Known Activations