© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93019
    Prev
    Next
    INDEX
    Explanations

    compulsory and free education systems

    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_11_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
    ニア
    0.61
     方法
    0.57
     定
    0.52
    ﾞ
    0.52
     универса
    0.51
     法
    0.50
     大
    0.49
    に参加
    0.49
     инструмента
    0.49
    4
    0.49
    POSITIVE LOGITS
     samme
    0.51
    同样的
    0.51
     upravo
    0.50
    permal
    0.50
    tox
    0.50
    period
    0.49
    habt
    0.49
    쎌
    0.49
    cells
    0.48
    perl
    0.48
    Activations Density 0.023%

    No Known Activations