© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104833
    Prev
    Next
    INDEX
    Explanations

    define scope or knowledge

    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_44_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
     Making
    0.43
     making
    0.39
     showcasing
    0.38
     empty
    0.38
     Quality
    0.38
     Jam
    0.37
     Qualitative
    0.36
    淉
    0.36
     Lets
    0.36
     NSObject
    0.35
    POSITIVE LOGITS
    ophytic
    0.40
    ongo
    0.39
    uerre
    0.38
    Shanghai
    0.37
    assumption
    0.36
    श्वर
    0.36
     পাঠক
    0.36
    zez
    0.36
    ませ
    0.35
    paralleled
    0.35
    Activations Density 0.026%

    No Known Activations