© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216760
    Prev
    Next
    INDEX
    Explanations

    legal codes

    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_47_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
    φορά
    0.44
     సంవ
    0.41
     merchand
    0.39
    ený
    0.39
     queuing
    0.38
    esto
    0.37
     resale
    0.36
    }}^{*
    0.35
     merchandising
    0.35
     resellers
    0.35
    POSITIVE LOGITS
    >]
    0.41
     Nih
    0.39
     Wilkes
    0.38
     शिवसेना
    0.37
     ऐप्स
    0.37
     dö
    0.37
    磔
    0.36
     छव
    0.36
     Avocado
    0.36
     Amber
    0.36
    Activations Density 0.000%

    No Known Activations