© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80067
    Prev
    Next
    INDEX
    Explanations

    fear

    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_53_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
    ナン
    0.41
     ওয়েবসাইট
    0.40
    руют
    0.39
    =("
    0.37
    жливо
    0.36
     Anyway
    0.35
    шт
    0.35
     Zol
    0.35
    ಚಿ
    0.34
     लर्निंग
    0.34
    POSITIVE LOGITS
    িয়ার
    0.44
    gery
    0.38
    iad
    0.38
    ेस
    0.37
    Բ
    0.37
     দেবার
    0.37
    SQLException
    0.37
    ે
    0.37
     مرا
    0.36
     मग
    0.36
    Activations Density 0.004%

    No Known Activations