© 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. 43870
    Prev
    Next
    INDEX
    Explanations

    toppings

    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
    DHL
    0.51
     سپورت
    0.51
    Sunset
    0.47
    FORMAT
    0.47
    ي
    0.46
    真正的
    0.46
    GST
    0.46
    чет
    0.46
     контро
    0.46
     فورم
    0.46
    POSITIVE LOGITS
    ers
    0.56
     P
    0.56
     peanut
    0.54
     Ι
    0.53
     alight
    0.52
     W
    0.48
    اٹ
    0.46
    ik
    0.46
     Housing
    0.46
     Peanut
    0.46
    Activations Density 0.007%

    No Known Activations