© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57727
    Prev
    Next
    INDEX
    Explanations

    each, każdy, đơn, EACH

    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_11_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
     Rodríguez
    0.48
    are
    0.46
    Е
    0.46
     menacing
    0.46
     acidified
    0.45
     pleasure
    0.44
     metabolic
    0.44
     broadened
    0.44
     network
    0.43
    ﻰ
    0.43
    POSITIVE LOGITS
     각
    0.48
     każdy
    0.46
     arrondi
    0.46
    但是
    0.46
     każde
    0.45
     đơn
    0.45
    誰
    0.45
    ependant
    0.44
     cependant
    0.44
     EACH
    0.43
    Activations Density 0.000%

    No Known Activations