© 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
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216390
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Blackboard
    0.44
    esk
    0.40
    uer
    0.38
    esy
    0.37
    偲
    0.37
    Short
    0.36
    Посилання
    0.36
     Kid
    0.36
     Peel
    0.36
    uz
    0.36
    POSITIVE LOGITS
    鉈
    0.38
    דת
    0.38
     NDP
    0.38
    팬
    0.38
    }}(\
    0.37
    壴
    0.37
     ir
    0.36
    អនុ
    0.36
     Oph
    0.36
     thymus
    0.36
    Activations Density 0.003%

    No Known Activations