© 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. 2441
    Prev
    Next
    INDEX
    Explanations

    System.out

    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
    緞
    0.45
    বাঁ
    0.43
    傕
    0.41
    入場
    0.40
     Bout
    0.38
    Drone
    0.38
     помощ
    0.37
     nutric
    0.37
    点
    0.36
    營養
    0.36
    POSITIVE LOGITS
     out
    0.66
    出来
    0.42
     subst
    0.41
    出的
    0.41
    出来的
    0.39
     outta
    0.39
    出一个
    0.38
     tell
    0.37
     পরও
    0.37
     JG
    0.36
    Activations Density 0.003%

    No Known Activations