© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164906
    Prev
    Next
    INDEX
    Explanations

    systems, version, running

    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_13_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
    在
    0.50
    意外
    0.47
     algebraica
    0.47
     erset
    0.46
    モー
    0.46
    ヒ
    0.45
     amikor
    0.45
    グ
    0.45
    屼
    0.45
    沢
    0.45
    POSITIVE LOGITS
    holt
    0.58
    dal
    0.57
    det
    0.56
    odt
    0.54
    ocom
    0.53
    GBT
    0.52
    ds
    0.52
    od
    0.51
    ana
    0.51
     Матери
    0.51
    Activations Density 0.000%

    No Known Activations