© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    page name components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     پہلے
    1.67
     पहले
    1.48
    UITableView
    1.40
     आल्स
    1.39
     polynomials
    1.38
    攽
    1.38
    ি
    1.35
     bangsa
    1.35
     promulgating
    1.34
     hiatus
    1.34
    POSITIVE LOGITS
    ж
    1.71
     pust
    1.32
     fal
    1.32
    s
    1.26
    ut
    1.25
     habido
    1.20
    phone
    1.15
     stav
    1.13
    ada
    1.13
    知道
    1.10
    Activations Density 0.003%

    No Known Activations