© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33954
    Prev
    Next
    INDEX
    Explanations

    flu or flow

    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_50_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
    ouri
    0.40
    यॉर्क
    0.40
    Postfix
    0.38
    DropDown
    0.38
    节
    0.37
    iov
    0.37
    by
    0.36
    ourg
    0.36
    orous
    0.36
     сокра
    0.36
    POSITIVE LOGITS
     Jair
    0.41
     PROJECTS
    0.41
    चुर
    0.40
     Botany
    0.39
     проекты
    0.38
     Projects
    0.38
    낮
    0.38
    婳
    0.38
    uke
    0.38
    坟
    0.38
    Activations Density 0.002%

    No Known Activations