© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2326
    Prev
    Next
    INDEX
    Explanations

    LEGO, tiny, local, boat parts, plastic clasp

    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_40_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
     سلاٹ
    0.22
    basename
    0.19
    টিয়
    0.19
    ステム
    0.19
    ጣም
    0.19
     quantile
    0.19
    Residual
    0.19
    ቑ
    0.19
    पूर्ण
    0.18
    Executable
    0.18
    POSITIVE LOGITS
     httpServer
    0.21
     pe
    0.20
     humanist
    0.20
     vi
    0.19
     sû
    0.19
     paprika
    0.19
     warming
    0.19
    黄色
    0.19
     흰
    0.19
     decorating
    0.19
    Activations Density 0.470%

    No Known Activations