© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 164888
    Prev
    Next
    INDEX
    Explanations

    modal, dialog, popup, app

    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_31_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
    ન્મ
    0.35
     blame
    0.34
    uvat
    0.34
     সার্ভ
    0.34
     ભ
    0.33
    ванням
    0.33
     характеристики
    0.33
    ວຍ
    0.33
    漆
    0.33
    ował
    0.33
    POSITIVE LOGITS
    Modal
    0.44
     modals
    0.39
     ሚ
    0.36
     সংসারে
    0.35
     dinner
    0.35
     সংসার
    0.34
     সংসারের
    0.34
    Interstitial
    0.34
     cohes
    0.33
     मर्
    0.33
    Activations Density 0.001%

    No Known Activations