© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196958
    Prev
    Next
    INDEX
    Explanations

    vec

    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_46_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
    Duck
    0.40
    萑
    0.38
    jahr
    0.36
    ümü
    0.36
    uffled
    0.36
    ချ
    0.36
    Tested
    0.36
    
    0.36
     cherished
    0.36
     কমলনগর
    0.35
    POSITIVE LOGITS
     raisin
    0.41
     Reck
    0.40
    一行
    0.37
     পরা
    0.37
    সন্ত
    0.37
    ጠን
    0.36
    isson
    0.35
    霸
    0.35
    INVALID
    0.35
    熟悉
    0.35
    Activations Density 0.001%

    No Known Activations