© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259692
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    ratulations
    1.20
    س
    1.19
    נים
    1.17
    在
    1.16
     spears
    1.14
    ták
    1.14
     اهو
    1.10
    た
    1.09
     मंत्रि
    1.09
    চে
    1.07
    POSITIVE LOGITS
     paradigm
    1.20
    τό
    1.18
     el
    1.14
     dtype
    1.12
    тон
    1.11
    主義
    1.10
     aún
    1.09
    лла
    1.08
    couvrez
    1.03
     Simul
    1.02
    Activations Density 0.000%

    No Known Activations