© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137225
    Prev
    Next
    INDEX
    Explanations

    menus and options

    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_37_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
    加拿
    0.39
     misure
    0.38
     Subsect
    0.38
    Episodes
    0.37
     sinusoid
    0.36
     সোভিয়ে
    0.35
    䟺
    0.35
    ადგენ
    0.35
     tang
    0.35
     signes
    0.35
    POSITIVE LOGITS
     lemak
    0.42
    ネ
    0.40
    વાદ
    0.38
    স্ব
    0.37
     UR
    0.36
    蓋
    0.36
    দেবের
    0.36
    Invite
    0.35
     ווי
    0.34
     मै
    0.34
    Activations Density 0.001%

    No Known Activations