© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110131
    Prev
    Next
    INDEX
    Explanations

    i i i

    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_2_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
    는
    1.80
    は
    1.69
    是
    1.55
    ي
    1.54
    ی
    1.40
    is
    1.37
    し
    1.34
    ли
    1.31
    ות
    1.28
    ር
    1.27
    POSITIVE LOGITS
    p
    1.31
    ne
    1.28
    for
    1.28
     for
    1.26
    T
    1.23
    k
    1.19
    aj
    1.15
    ala
    1.08
    se
    1.07
    have
    1.06
    Activations Density 0.000%

    No Known Activations