© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245538
    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_11_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
    বর্তী
    1.29
    ೆ
    1.25
    िम
    1.22
    ्स
    1.19
    eur
    1.17
     styl
    1.17
    salir
    1.16
    
    1.15
    ክምና
    1.14
    cargar
    1.14
    POSITIVE LOGITS
    ने
    1.18
     őket
    1.10
     Tipps
    1.10
     τό
    1.09
     bruises
    1.08
     forbidding
    1.07
     doings
    1.06
    ると
    1.06
     ट्रांसजेंडर
    1.06
     barras
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.