© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117232
    Prev
    Next
    INDEX
    Explanations

    storage space

    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_27_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
    гыз
    0.35
    矿
    0.33
    हासन
    0.32
     چاہیے۔
    0.32
     ہوگی
    0.31
    ޤ
    0.31
    编译
    0.31
     प्रमेय
    0.31
     ہوگا۔
    0.31
    貽
    0.31
    POSITIVE LOGITS
     carried
    0.37
    lices
    0.34
     V
    0.34
     ஒப்ப
    0.33
     gla
    0.33
     Μα
    0.32
     sought
    0.32
     ending
    0.32
     pleasing
    0.32
    ডস
    0.32
    Activations Density 0.000%

    No Known Activations