© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203293
    Prev
    Next
    INDEX
    Explanations

    diversification

    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_6_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
    ва
    1.29
     allez
    1.17
    arı
    1.12
    ем
    1.10
    ер
    1.09
     bạn
    1.09
     effectuées
    1.08
    ﺮ
    1.08
     shēng
    1.05
    ПА
    1.02
    POSITIVE LOGITS
    :
    1.51
    د
    1.48
    )
    1.45
    д
    1.45
    z
    1.40
    س
    1.39
    in
    1.36
    o
    1.34
    _
    1.31
    at
    1.27
    Activations Density 0.001%

    No Known Activations