© 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. 197255
    Prev
    Next
    INDEX
    Explanations

    file path or graphics shader

    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
    ஜ
    0.18
    痙
    0.17
     Pineapple
    0.17
    <0xDB>
    0.16
    ក
    0.16
    OJ
    0.16
     Originally
    0.16
    浿
    0.16
    getInputStream
    0.15
     তোর
    0.15
    POSITIVE LOGITS
    牫
    0.16
     reflect
    0.16
     commerciali
    0.15
     persist
    0.15
     більш
    0.15
     alkenyl
    0.15
     unem
    0.14
     vign
    0.14
     tồn
    0.14
     DevOps
    0.14
    Activations Density 0.002%

    No Known Activations