© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240099
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific integers

    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_25_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
    느
    0.34
    하고
    0.31
    ವಾಗ
    0.27
     بنگ
    0.27
     isch
    0.26
     المح
    0.26
    [{}\
    0.26
     نئے
    0.25
    𝗺
    0.25
    IUM
    0.25
    POSITIVE LOGITS
     Compd
    0.34
    汇总
    0.32
     pleasant
    0.31
     loyalty
    0.29
    奂
    0.29
     sabía
    0.28
    érrez
    0.28
     judicious
    0.28
    䔀
    0.28
     compactness
    0.28
    Activations Density 0.021%

    No Known Activations