© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139499
    Prev
    Next
    INDEX
    Explanations

    号, 匹, 场, 句, 词

    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_37_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
     Mang
    0.39
    一张
    0.38
    PD
    0.38
    ⚛
    0.37
    nickel
    0.36
     प्राथमिकी
    0.35
    omega
    0.34
     парт
    0.33
    রিটি
    0.33
    umap
    0.33
    POSITIVE LOGITS
    次的
    0.48
    次
    0.42
    數
    0.40
     Feria
    0.39
    ковский
    0.38
     Zahl
    0.37
     intervalo
    0.36
    数
    0.36
     reflexive
    0.35
     elimin
    0.35
    Activations Density 0.004%

    No Known Activations