© 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. 6403
    Prev
    Next
    INDEX
    Explanations

    Final Answer

    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
     எம்
    0.41
     dị
    0.39
     паро
    0.38
     depender
    0.38
     Nature
    0.38
     MD
    0.38
     természet
    0.37
    傕
    0.36
     steeped
    0.36
    IDING
    0.36
    POSITIVE LOGITS
    dW
    0.42
     चोर
    0.39
    Boat
    0.39
    Mist
    0.37
     SOL
    0.36
    Pel
    0.36
    Gets
    0.36
    婊
    0.36
    Children
    0.36
    irie
    0.36
    Activations Density 0.002%

    No Known Activations