© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124726
    Prev
    Next
    INDEX
    Explanations

    Romanian, Russian, and English phrases

    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_3_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
    ോ
    0.69
    ால
    0.68
    adolu
    0.66
    ہ
    0.65
     as
    0.61
    א
    0.59
    ジェクト
    0.58
    detection
    0.57
    ショップ
    0.57
    ゼロ
    0.57
    POSITIVE LOGITS
     (
    0.70
    va
    0.68
    y
    0.60
    是
    0.60
    nel
    0.59
    nem
    0.59
    т
    0.59
    »
    0.57
    着
    0.57
     December
    0.57
    Activations Density 0.010%

    No Known Activations