© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78534
    Prev
    Next
    INDEX
    Explanations

    country names

    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
     pube
    0.34
    वीण
    0.32
     अंक
    0.32
     প্রের
    0.32
     bangs
    0.32
     leans
    0.32
    馥
    0.31
     രണ്ട്
    0.31
     mache
    0.31
    лын
    0.31
    POSITIVE LOGITS
    SelectItem
    0.36
     pygame
    0.35
    шымта
    0.33
    战场
    0.33
    ʢ
    0.33
     เรีย
    0.32
    ąda
    0.32
     Felony
    0.32
    hythmic
    0.32
    場
    0.31
    Activations Density 0.010%

    No Known Activations