© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250615
    Prev
    Next
    INDEX
    Explanations

    body unit

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     总
    0.40
     收
    0.39
    ｄ
    0.39
     हि
    0.39
     mats
    0.39
     matar
    0.37
     اﻻ
    0.37
     חו
    0.36
     Porcelain
    0.36
     chc
    0.36
    POSITIVE LOGITS
    deoxy
    0.42
    至
    0.41
    架构
    0.41
    ICLE
    0.40
    district
    0.38
     district
    0.38
    supreme
    0.36
    体
    0.36
    fiction
    0.35
    體
    0.35
    Activations Density 0.000%

    No Known Activations