© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166801
    Prev
    Next
    INDEX
    Explanations

    **

    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_31_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
    TableAdapter
    0.39
     superior
    0.39
     reaches
    0.39
     successfully
    0.39
    zhu
    0.39
     overall
    0.38
     accomplishes
    0.38
    <^
    0.38
     completos
    0.38
    optimal
    0.37
    POSITIVE LOGITS
    গুলে
    0.41
     مذہبی
    0.41
     Crusade
    0.40
     мяс
    0.40
     სამ
    0.40
    燧
    0.40
     العلم
    0.39
     popOperand
    0.38
     দিতে
    0.38
     yapılan
    0.38
    Activations Density 0.000%

    No Known Activations