© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176857
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

    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_24_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
     ടീ
    0.35
     owning
    0.33
    ρίου
    0.31
     কিংবা
    0.31
    ؘ
    0.30
     option
    0.29
     Гуляць
    0.29
     ซึ่ง
    0.29
    旿
    0.29
     thats
    0.29
    POSITIVE LOGITS
    সি
    0.29
    EN
    0.29
    出现
    0.29
     Bibliothèque
    0.29
     सुगंध
    0.29
    udsman
    0.29
    火焰
    0.29
     मौ
    0.28
     mesa
    0.28
     समझाया
    0.28
    Activations Density 0.010%

    No Known Activations