© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48263
    Prev
    Next
    INDEX
    Explanations

    snakes and snout

    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_10_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
     চৈতন্ত
    0.36
    ﻝ
    0.34
    NOUN
    0.34
    }=\
    0.33
     ਪ
    0.33
     brooch
    0.33
     biosphere
    0.32
    ING
    0.32
    ੁ
    0.32
    LookAndFeels
    0.31
    POSITIVE LOGITS
    k
    0.46
    ক
    0.43
    s
    0.42
    h
    0.38
    اقة
    0.37
    name
    0.36
    ad
    0.35
    th
    0.35
    b
    0.35
    ב
    0.34
    Activations Density 0.024%

    No Known Activations