© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18777
    Prev
    Next
    INDEX
    Explanations

    smithsonianmag.com, news, geographic, lemonde.fr

    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_15_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
    hur
    0.52
    role
    0.49
    t
    0.45
    Queries
    0.44
    ser
    0.44
    calcul
    0.43
    ږئ
    0.42
    ෲ
    0.42
     t
    0.42
    worms
    0.42
    POSITIVE LOGITS
     Educational
    0.59
     Azərbaycan
    0.53
     CGA
    0.53
     CWE
    0.52
     Award
    0.52
     Investigator
    0.52
     Samen
    0.52
     Subsequent
    0.51
     Skate
    0.51
     Гра
    0.51
    Activations Density 0.085%

    No Known Activations