© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259473
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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_22_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
     C
    0.31
     Base
    0.29
    Faction
    0.28
     Re
    0.28
     ה
    0.28
     eer
    0.28
    PS
    0.28
     This
    0.28
     History
    0.27
     R
    0.27
    POSITIVE LOGITS
    十二章
    0.31
    мера
    0.28
    。）
    0.28
     malattia
    0.28
     biolog
    0.27
    ̀n
    0.27
    跇
    0.27
    ӯ
    0.26
    簀
    0.26
     पनि
    0.26
    Activations Density 0.001%

    No Known Activations