© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44098
    Prev
    Next
    INDEX
    Explanations

    alpha particles, helium

    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_13_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
    Elizabeth
    0.49
    DE
    0.48
    water
    0.48
    over
    0.47
    h
    0.46
     पदा
    0.46
    Ed
    0.45
    Unexpected
    0.45
    RE
    0.45
    time
    0.45
    POSITIVE LOGITS
     ტ
    0.54
     Alright
    0.53
     ইন্ড
    0.49
     ölç
    0.49
    тился
    0.47
    тел
    0.47
     Kanpur
    0.47
     Keenan
    0.47
     Khud
    0.47
    ビス
    0.46
    Activations Density 0.020%

    No Known Activations