© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145842
    Prev
    Next
    INDEX
    Explanations

    savanna

    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_0_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
    та
    1.86
    দের
    1.38
    ти
    1.36
    وں
    1.35
    ის
    1.34
    يا
    1.34
    ール
    1.27
    с
    1.27
    и
    1.25
    тэй
    1.22
    POSITIVE LOGITS
    。
    2.33
    a
    2.19
    ।
    2.19
    o
    2.14
    de
    1.91
    i
    1.75
    ed
    1.58
    f
    1.50
    0
    1.49
    {
    1.46
    Activations Density 0.000%

    No Known Activations