© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28885
    Prev
    Next
    INDEX
    Explanations

    places like airport, city, park, station

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    LinkClicked
    0.39
    >-->
    0.36
     شوی
    0.35
    স্টে
    0.33
    ्व
    0.32
     ओह
    0.32
     zej
    0.32
    '])->
    0.32
    诡
    0.32
    АСС
    0.31
    POSITIVE LOGITS
     सर्वात
    0.37
     Paulus
    0.34
    模式
    0.32
    मेंट्स
    0.32
     સૌથી
    0.32
     APIs
    0.32
     sight
    0.31
     buddha
    0.31
     ∫
    0.31
     larges
    0.30
    Activations Density 0.009%

    No Known Activations