© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198147
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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_50_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
     verw
    0.53
    Ed
    0.47
    Pars
    0.40
    anchen
    0.38
    骊
    0.37
     Siri
    0.37
    ಹೆ
    0.37
    Eligibility
    0.37
    Ꮮ
    0.37
    paren
    0.36
    POSITIVE LOGITS
     Consol
    0.44
     ce
    0.40
    гом
    0.39
     constitu
    0.38
     sacred
    0.38
     Yoh
    0.37
     Wm
    0.37
    หม
    0.37
     '--
    0.37
     Mad
    0.36
    Activations Density 0.003%

    No Known Activations