© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198036
    Prev
    Next
    INDEX
    Explanations

    Estonian

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     PAT
    0.52
    PAT
    0.48
     pat
    0.42
     Siro
    0.41
    媤
    0.41
     valu
    0.40
    itesi
    0.40
     สิ
    0.40
     패
    0.40
     sii
    0.40
    POSITIVE LOGITS
    ta
    0.41
     Taf
    0.41
    Taj
    0.40
    ピン
    0.39
     taj
    0.38
     Taj
    0.38
     Тай
    0.37
     approximations
    0.37
    ose
    0.37
    মাণের
    0.37
    Activations Density 0.000%

    No Known Activations