© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220598
    Prev
    Next
    INDEX
    Explanations

    Victoria, places, and victoria meaning Victory

    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_31_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
    韩
    0.38
    韓
    0.38
     Rudi
    0.37
    aste
    0.35
    keiten
    0.35
    actifs
    0.34
    activated
    0.34
    ()+
    0.34
    texttt
    0.34
     :]
    0.34
    POSITIVE LOGITS
     silage
    0.43
     Carriage
    0.43
     bodice
    0.40
     carriage
    0.40
     महार
    0.40
     sunshine
    0.40
     sill
    0.40
     gown
    0.39
     upkeep
    0.39
     scrumptious
    0.39
    Activations Density 0.001%

    No Known Activations