© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195572
    Prev
    Next
    INDEX
    Explanations

    more than any other group

    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_26_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
    жы
    0.46
    ༨
    0.45
     класса
    0.45
     работа
    0.43
     Ирина
    0.42
    免疫
    0.42
     Orts
    0.41
    齦
    0.41
    ሪ
    0.41
     ప్రభ
    0.41
    POSITIVE LOGITS
     également
    0.42
     makeup
    0.39
    iken
    0.39
     ballad
    0.38
     அவற்ற
    0.37
    လည်း
    0.37
    henol
    0.37
     breakout
    0.36
     numerous
    0.36
     Garrett
    0.35
    Activations Density 0.000%

    No Known Activations