© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26999
    Prev
    Next
    INDEX
    Explanations

    module or modular

    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_10_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
    ला
    0.47
    स
    0.46
    اد
    0.46
    사
    0.45
    ad
    0.41
    토
    0.41
    را
    0.40
    ALES
    0.40
    보
    0.40
    ون
    0.39
    POSITIVE LOGITS
     моду
    0.54
     modular
    0.53
    ),
    0.43
    </td>
    0.43
    יות
    0.43
     módulos
    0.43
    ي
    0.43
     добав
    0.42
     Modular
    0.41
    и
    0.41
    Activations Density 0.005%

    No Known Activations