© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100753
    Prev
    Next
    INDEX
    Explanations

    terminal commands and output

    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_14_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
    le
    0.51
     Products
    0.51
     G
    0.50
    工
    0.49
     Firm
    0.48
    ర్లు
    0.47
     Road
    0.46
     Group
    0.45
     Mass
    0.45
     MRT
    0.45
    POSITIVE LOGITS
    屜
    0.54
     membranes
    0.54
    UP
    0.50
     membran
    0.48
    ರವಾಗಿ
    0.48
    observations
    0.47
     manifesting
    0.47
    offrey
    0.46
    UCLEAR
    0.46
     powdered
    0.46
    Activations Density 0.000%

    No Known Activations