© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14132
    Prev
    Next
    INDEX
    Explanations

    graphene and tape exfoliation

    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_13_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
     Katherine
    0.57
     dne
    0.54
     kur
    0.54
     Australia
    0.53
     Erg
    0.53
     Montana
    0.51
     Judd
    0.50
     '=',
    0.48
     Brand
    0.48
     alfabet
    0.48
    POSITIVE LOGITS
    碎片
    0.53
    Plate
    0.53
    BottomSheet
    0.52
    Freight
    0.51
    Square
    0.50
    pload
    0.50
    úp
    0.49
    Dispatch
    0.49
    Authenticate
    0.49
    Exclude
    0.48
    Activations Density 0.017%

    No Known Activations